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

Annotations only cover readOnly/openWorld, but the description adds substantial behavioral context beyond them: the count is approximate and why (double-counting establishments, SIREN substring matches), suspect/aberrant amounts are excluded, amounts are buyer-declared ceilings excl. VAT and not spend/revenue, and page size is fixed at 20. These are exactly the caveats an agent needs to interpret results.

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?

Dense but front-loaded: the primary noun phrase and returned fields lead, caveats follow. It is long and runs as a single block with semicolons rather than scannable structure, but nearly every clause carries informational weight.

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, the description carries the full return-value burden and does so thoroughly: itemized fields, pagination order, and the company status fields (active, insolvency proceeding). Nothing essential for correct invocation or interpretation is missing.

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 75%, already documenting from/to ('Notified on or before/after') and page ('Page of 20 contracts'). The description largely restates those (notification dates, 20 per page) and adds nothing about the undocumented siren parameter, so it sits at the schema-driven baseline.

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 precise verb+resource: returns public contracts a French company won, sourced from DECP procurement data, with a concrete enumeration of what comes back (count, summed max amounts, first/latest notification, paginated contract list). An agent can distinguish this from get_company or get_establishment 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?

Gives clear selection context (this is the DECP public-procurement view rather than general company data) and an explicit narrowing instruction: 'Narrow with from and to (notification dates).' It does not, however, name a sibling alternative or state when NOT to use it, so it stops short of full routing guidance.

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