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

Annotations already cover safety (read-only, idempotent, non-destructive), so the bar is lower. The description adds valuable behavioral context beyond annotations: the HTTP method, a deterministic similarity score, the fact that a score_explanation is present, the cost, and the temporal scope ('active/recent'). This goes beyond what annotations or schema alone provide.

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 sentence that front-loads the endpoint, cost, and primary data scope, then adds the differentiating scoring mechanism. Every clause contributes new information with no filler or repetition of schema content.

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 no output schema, the description explains the core purpose and mentions the score_explanation field, which helps an agent know what to expect in the response. Pagination is handled by schema defaults, and payment/auth by parameter descriptions. The only minor gap is whether score_explanation is per-item or top-level, but this is not critical for invoking the tool correctly.

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 60% (id, client_key, payment_token are described; page and size are not). The description indirectly explains id by referencing a company's profile and clarifies the conceptual output, but it adds little direct parameter-level meaning. Page/size remain only semantically inferable from defaults, and the payment parameters are fully described in the schema. The description partially compensates, but not fully.

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 the specific resource ('opportunities' for a company) and a concrete action (retrieving active/recent tenders), plus a distinctive matching mechanism ('historical CPV/buyer profile' with a 'deterministic similarity score'). This clearly separates it from siblings like search_tenders, get_company_awards, and get_buyer_history without needing to open the schema.

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 when to use the tool: when you need tenders matching a particular company's profile. However, it does not explicitly state when not to use it, nor does it name any alternative tools or conditions for choosing them. The usage context is clear from the phrasing but not fully spelled out.

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