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

Annotations already declare read-only, open-world, idempotent and non-destructive, so the burden is lighter. The description adds real behavioral context beyond the schema: free tier vs. caller's API key for auth, a SHA-256 proof of the TED answer, and cursor-based polling semantics for newly stored awards.

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?

A single dense paragraph that front-loads what the tool returns before covering filters and paging. Every sentence carries information, though the field enumeration in the opening clause is long and could be tightened.

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 takes on the job of describing return content — and does so (winner, buyer, value, CPV, dates, lots, notice link, proof hash). Combined with 7 fully documented parameters and rich annotations, the only missing piece is explicit differentiation from get_eu_contract_award.

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 100%, so the baseline is 3; the description's mapping of the "has company X won since D" question onto winner + since, and its explanation that winner means name prefix while winner_id means official identifier, add modest interpretive value. It does not add syntax detail beyond the schema, so it does not reach 5.

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 — EU public contracts awarded from official TED contract award notices — and enumerates the fields returned (winner, buyer, value, CPV, country, dates, lots). It is clear what the tool does, but it never names the singular sibling get_eu_contract_award to say how listing differs from fetching one award.

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 concrete usage patterns: use since for new awards, filter by CPV/buyer country/winner to answer "has company X won anything since D", and pass next_cursor back as cursor to page or poll. This is strong contextual guidance, though there is no explicit when-not or pointer to a sibling alternative.

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