suivi_verifier

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

With no annotations, the description carries the burden and does well: it discloses that writing requires both `ecrire=True` and `URSSAF_ECRITURE=1`, specifies which columns are updated, and makes clear that omitting `ecrire` performs a simulation. It does not mention error handling or return values.

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 a single dense but front-loaded sentence that puts the primary action first and layers conditions efficiently. It is somewhat packed with parenthetical detail, but no sentence is wasted.

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 three-parameter mutation tool with no annotations and no output schema, it covers the main write behavior and dry-run semantics but omits the `fichier` parameter and does not say what the verification returns. It is adequate but has clear gaps.

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 0%, so the description must compensate. It clearly explains `tous` and `ecrire`, but it never defines the `fichier` parameter or its expected format/path, leaving one of three parameters undocumented.

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 states a specific verb and resource: verifying Urssaf codes in the tracking table and optionally writing results. It is clearly distinct from the attestation-focused siblings, though it does not explicitly name those alternatives.

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?

It explains the default mode (only unchecked codes), the `tous=True` override for monthly re-checks, and the simulation behavior when `ecrire` is omitted. Usage is clear, but it does not route the agent against sibling tools or state exclusions.

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