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

Annotations already declare readOnlyHint=true, idempotentHint=true, and openWorldHint=true. The description adds behavioral context beyond this: 'Name matching is partial' and 'Returns the buyer's awards newest first' plus summary details. It also clarifies the data scope (above-threshold EU procurement). This is meaningful additional context about matching and return ordering, but doesn't cover every edge case (e.g., pagination behavior), so a 4 is appropriate.

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 three sentences and front-loaded: it states the core purpose and output in the first sentence, then enriches with use cases and limitations. Every sentence earns its place; no fluff or repetition of schema fields. This is an exemplary concise structure.

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 read-only profile tool with 8 parameters and no output schema, the description covers key behavior (newest-first sorting, summary fields, partial name matching, above-threshold coverage) and practical use cases. It doesn't explicitly mention pagination or empty-result behavior, but those are inferable from the schema. Overall, it's comprehensive enough for an agent to select and invoke the tool correctly, with minor gaps.

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%, with each parameter documented (e.g., buyer 'matched partially', category 'Plain-English category resolved to CPV'). The description adds general context but does not introduce new parameter-level semantics beyond the schema. Per calibration, when schema coverage is high, baseline 3 is used, and the description doesn't significantly exceed that.

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 the tool's function: 'Spending profile of one EU public buyer — what a named contracting authority has AWARDED'. It specifies the resource (one EU buyer), the action (returns awards and summary), and scope (above-threshold TED data). It also distinguishes itself from sibling tools like ted_search_awards by focusing on a single buyer's profile rather than general search.

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 provides concrete example use cases: 'Use for "what does this ministry buy", "who are this city's incumbent suppliers", "what does Banedanmark spend on"'. It also notes coverage limitations ('Covers above-threshold EU procurement only — below-threshold national purchases appear on national portals'). However, it does not explicitly name alternative tools for when not to use this one, so it falls short of full when/when-not guidance.

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