controler_attestation

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

With no annotations at all, the description carries the full burden and does substantial work: it discloses that the tool reads the PDF, calls Urssaf to verify the code (an external dependency), and computes an explicit expiry rule (6 months after the analysed period, end of month). It also defines the three verdict tiers and the ALERTE threshold (<30 days). Gaps remain: it does not state that the operation is read-only/side-effect free, nor how Urssaf unavailability or unreadable PDFs are handled.

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 dense but well-formed blocks: the scope of the check first, the possible verdicts second. Front-loaded and free of filler, though the long parenthetical enumeration of checked fields is slightly list-like rather than prose.

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?

No output schema and no annotations, so the description is the only source of truth. It does define the verdict vocabulary and the validity rule, which is the critical return-value semantics. But it leaves the input contract incomplete ('fichier' format, 'domaine' meaning) and says nothing about side effects, failure modes, or cost/latency of the Urssaf lookup — significant for a tool that performs external verification.

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 0%, so the description must compensate. It does add real meaning for two of the four parameters by explaining that siret_attendu/siren_attendu define the 'cocontractant attendu' and feed the coherence check. But 'fichier' (the only required parameter) is never described — path, URL or base64 is unknown — and 'domaine' is entirely unexplained, which is the most damaging omission.

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?

States a specific verb and resource ('Contrôle complet d'une attestation reçue') and enumerates exactly what the check covers: PDF reading, Urssaf code verification, field-by-field coherence, cocontractant matching, validity window. It is clearly a heavier, composite operation than the sibling 'verifier_attestation', but the description never names the siblings or explicitly contrasts with them, so differentiation is only implied by the word 'complet'.

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 phrase 'attestation reçue' and 'Contrôle complet' imply this is the full end-to-end validation path, and the mention of siret_attendu/siren_attendu implies a cocontractant-matching use case. However, there is no explicit when-to-use versus 'verifier_attestation', 'verifier_attestations' or 'lire_attestation_pdf', and no stated preconditions or exclusions.

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