scan

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It covers key behaviors: return type (leads, not verdicts), output constraints (bounded, paged), response contents (coverage and temporal work completion), concurrency semantics (serialized per session), and runtime selection (native selected internally). This is comprehensive and leaves little ambiguity about side effects or state.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is succinct and front-loaded with the core purpose, then transitions to lens options and finally operational details. It avoids redundancy and stays within a few sentences. The structure is logical, though the multiple clauses about behavior could be slightly more organized with bullets, but overall it is well-compact.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with 8 parameters, no output schema, and no annotations, the description covers the essential context: what it returns (questions), how results are bounded/paged, that response includes coverage and temporal status, and that calls are serialized. It does not describe the exact output format (e.g., JSON structure) or elaborate on all param semantics, but given the complexity, it leaves only minor gaps that the schema partially covers.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 63%, so the schema already documents several parameters (lens, format, offset, hard_stop, entrypoints). The description adds semantic meaning for 'lens' (all vs. guard-diff vs. flow) but does not elaborate on the meanings or interactions of the undocumented parameters (limit, min_rank, include_suppressions). Given the moderate coverage, the description only partially compensates, so a baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb-resource pair: 'Return ranked leads' from the whole taxonomy. It further clarifies the output nature ('questions to investigate, never verdicts') and provides lens-specific variants. It clearly differentiates itself from the sibling tools that focus on specific analysis (e.g., flow, guard_dominance) by mentioning distinct lens modes. This is unambiguous and minimally overlapping with sibling names.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly instructs when to use alternative lens views: 'Use lens=guard-diff for the entrypoint-to-effect guard view or lens=flow for native object-lifetime leads.' It also sets expectations about results being bounded and paged, and mentions the serialized nature of calls. This gives the agent clear decision criteria without needing to infer.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.