Quant Swarm Audit — Export Reproducible Evidence Report

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive, closed-world, so safety is largely covered. The description adds real context beyond that by enumerating the finding taxonomy (OBSERVED_PROBLEM | SENSITIVITY_WARNING | INSUFFICIENT_EVIDENCE | PASSED | NOT_TESTED) and the per-finding fields, which tells an agent what the output is good for. It does not disclose that the output_*_path parameters cause files to be written to disk or what happens on overwrite — a mild tension with readOnlyHint that an agent would want resolved.

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?

Two sentences, front-loaded with the deliverable, no filler. The second sentence is dense but earns its place by defining the finding contract an agent would otherwise have to discover from the output schema.

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?

An output schema exists and annotations cover the safety profile, so the description's remaining burden is small: what the tool produces and what the findings contain, both of which it states. The only gap, disk-write behavior for the optional paths, is a minor addition rather than a blocking omission.

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 description coverage is 100%, so each of the four parameters (including the three optional output paths) is already documented in the schema. The description adds nothing parameter-specific, so the baseline 3 applies.

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 and enumerated artifacts: 'Generates the structured JSON audit bundle, reproducibility manifest, and shareable HTML/Markdown reports.' That clearly separates it from audit.run (executes) and audit.status (polls), even though no sibling is named explicitly.

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?

Usage is only implied by the verb 'Generates' and the tool name. The prerequisite (a completed job_id from audit.run) and the alternative of just polling audit.status are stated only in the schema's job_id description, not in the tool description itself. No when-not guidance is given.

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