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

Annotations already declare readOnlyHint=true, but the description adds valuable behavioral context: real-time freshness ('Données fraîches à chaque appel') and a cost of 0.030 USDC. It does not contradict the annotation, and the price disclosure exceeds annotation coverage.

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 compact and front-loaded with the primary purpose, then lists filters, freshness, and price in a somewhat run-on sentence. It is efficient, though the single-sentence structure could be broken up for better readability.

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 does not explain the response format beyond the existence of 4,400+ contracts. It also omits the payment flow (e.g., needing payment_tx_hash or receiving payment instructions) which is only in the parameter description. This leaves gaps for an agent about how results are returned and how payment works.

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?

The input schema fully describes all 5 parameters (100% coverage). The description merely restates the filters (nature, année, pagination) already present in the schema, adding no additional semantic detail beyond what structured fields provide.

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 clearly states it fetches public contracts ('Marchés publics') for Guadeloupe (971) in real time from the official DECP database. This specific verb+resource+scope distinguishes it from the sibling 'caribbean_get_marches_publics_dom' which likely covers all French overseas territories.

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 implies use when Guadeloupe public contracts are needed, but does not explicitly contrast with the DOM-wide sibling. It lacks explicit when-to-use vs. alternative guidance, though the geographic scope is a clear contextual signal.

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