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

Annotations already declare readOnlyHint=true and openWorldHint=true, and the description adds substantial behavioral context beyond that: the data is 'facts only, no score', the absence semantics are explicitly disclosed, the pagination limit (100 each, `tronque_*`), the totals fields, and the licensing (OGL v3). It also discloses the payment behavior (x402 vs api_key, and the credits error path). This is rich behavioral disclosure.

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 dense and information-rich, front-loading the core purpose and data sources before the caveats and payment details. It is long, but every sentence carries meaningful information that an agent needs. Slightly over-stuffed, but not wasteful.

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?

Given the output schema exists and the annotations cover safety, the description is complete: it explains the data sources, the matching key, the fields returned, the pagination, the absence semantics, the licensing, and the payment options. An agent has everything needed to call this tool correctly and interpret the result.

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 100%, so the schema already documents all three parameters. The description adds context about the company_number format (leading zeros) and the payment flow, but the parameter semantics are largely carried by the schema. Baseline 3 is appropriate.

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 names a specific verb and resource ('Public-procurement record of a UK company'), identifies the two data sources (Find a Tender and Contracts Finder), and distinguishes the two directions of data (contracts WON vs notices ISSUED). It clearly differentiates from siblings like get_french_company_public_procurement and get_latvian_company_public_procurement by the UK scope and the named feeds.

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 on when the data is meaningful: it explains that only about half of suppliers carry a company number, that natural persons never do, and that `aucune_attribution: true` is non-conclusive while `aucun_marche: true` is conclusive. It does not explicitly name alternative tools for when this one is not appropriate, but the coverage caveats effectively tell the agent when the result is not conclusive.

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