Get a site's expert report

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

No annotations are provided, so the description carries the full load, and it does so well: it discloses that it never triggers an analysis, that a missing analysis yields status "NONE", that in-progress states require a retry, and that full/expert change payload size. It does not mention permissions or rate limits, but the state-machine behavior is a genuinely useful disclosure beyond structured fields.

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?

Front-loaded with the core purpose, then parameter behavior, then the non-trigger/status semantics, and every sentence carries information. The enumeration of eight experts is long but legitimately informative; the single dense paragraph is slightly harder to scan than a structured layout would be.

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?

With no output schema and no annotations, the description fills most gaps: it describes the returned content (findings, actions, limits, artifacts, proofs) and the status outcomes. It is nearly complete for a report-retrieval tool, though the exact shape of the "NONE/PENDING/RUNNING" response and any pagination are not spelled out.

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 100%, so the baseline is 3, but the description adds real meaning: full=true adds justification/limits/artifacts/proofs on top of the default summary, expert limits reading to one chapter and is "utile avec full=true", and auditId chooses a specific analysis versus the site's most recent one. This augments rather than repeats the schema.

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?

It opens with a specific verb ("Récupère") and resource ("le dernier rapport de nos 8 experts"), enumerates the eight expert chapters, and details exactly what each report contains (constats priorisés, actions, artefacts). An agent can distinguish this read-only report fetcher from siblings like run_audit or get_audit without opening any schema.

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?

The description gives clear context and an explicit when-not: "Ne déclenche PAS d'analyse", plus the retry condition "PENDING/RUNNING = réessayer plus tard", and when to use expert with full. It stops short of naming the sibling to call instead (e.g. run_audit) to trigger an analysis, so it is strong but not fully explicit about the alternative.

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