No two tools share an identical description
Authored by Stanley Hong · AgentReserve (founder).
Within the advertised `tools/list`, no two distinct tools share a byte-identical (post-trim) non-empty description. Within-server duplicate descriptions catch two failure modes: lazy / autogenerated catalogs where every tool reads the same boilerplate, and the camouflage pattern where a malicious tool inherits a benign sibling's description verbatim so a side-by-side reviewer can't tell them apart.
When this rule runs
Requires a successful MCP `initialize` / `tools/list`. Skipped on perimeter-only scans where the server refused or failed the MCP handshake.
Why it matters
Tool descriptions drive both human review and the model's interpretation of which tool to call. Two tools advertising the same description means at least one is mis-described — the reviewer can't tell them apart, and the agent has no way to choose between them without invoking one. Empty / missing descriptions are excluded; the dedicated `all_tools_have_descriptions` rule covers that case.
Pass condition
Every non-empty tool description is unique across the advertised tools/list.
Fail condition
At least two tools share a byte-identical (post-trim) non-empty description.
Evidence examples
When the rule fails, the report records evidence in roughly this shape:
{"hits": [{"toolNames": ["delete_files", "list_files"]}]}
Remediation
Write each tool description for the specific tool. If two tools genuinely do the same thing, merge them. If one is intentionally a thin wrapper, say so — `"Convenience wrapper for X with Y enabled."` is fine; verbatim copies are not.
Methodology
This rule belongs to the Metadata transparency dimension. Whether the server identifies itself and documents its tools — and whether the advertised identity matches the wire identity (cert CN/SAN, hostname). Operators need a stable name, a version, and an internally consistent identity claim to perform any kind of audit.
Read the full methodology for how rules are aggregated into a score, how verdicts are decided, and how hard-fail rules override the aggregate.