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

With no annotations, the description carries the full burden and does well: it discloses the 25-notice cap and newest-first ordering, that results come from a third-party seller (Atlas Data), that responses are cached up to 1 h, and that each call costs 0.03 USD via x402. It does not describe failure modes (e.g., what happens when the budget/payment fails) or a rate limit, which keeps it short of a 5.

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?

Front-loads the verb and resource, then packs filters, return fields, ordering, caching, provenance and price into tightly written sentences with no repetition. The copyright/price tail is short and operationally relevant rather than filler.

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 10-parameter, no-output-schema, paid third-party search tool, the description covers query semantics, result shape, result cap/ordering, caching, cost and licensing — everything an agent needs to decide to call it and interpret the response.

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 baseline is 3, but the description adds real value where the schema is thin — it clarifies noticeType with examples ("calls for tenders, awards, planning…") where the schema only says "Default any", and restates onlyOpen as "only tenders still open". That compensates for the one weak parameter definition.

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 ("Search EU public procurement notices on TED") and then enumerates the filterable dimensions (keyword, buyer country, CPV, notice type, publication date, open-only) plus the fields returned. No sibling tool covers tenders, so it is trivially distinguishable from the dk_/eu_ utility tools, and an agent can tell exactly what domain it queries.

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 context for use: filter by keyword/country/CPV/notice type/date, and "optionally only tenders still open". Defaults are implied for dates (schema says 30 days) and result count. It does not state when NOT to use it or any prerequisite/failure conditions, but there is no competing sibling to route against.

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