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

Annotations only assert readOnlyHint and openWorldHint=false; the description adds real behavioral context beyond that: 'Free during beta' (cost), the closed public-records provenance, the geographic caveat that Portugal yields materially richer data (entered contests, win rate, rivals, losses), and the constraint 'report facts, not conclusions about wrongdoing'. It does not mention pagination or result-size limits.

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?

No output schema exists, so the return-field enumeration earns its place, but it is delivered as one very long semicolon-chained sentence and the leading 'Free during beta' front-loads pricing instead of purpose. Dense and waste-free, yet poorly structured for scanning.

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 correctly carries the burden of describing returns and does so exhaustively, including the Portugal-only extras. Safety is already covered by readOnlyHint. Minor gaps remain: no default time range, no pagination/result-size behavior, and ambiguity between the 'countries' input filter and the countries listed as outputs.

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 company, since, and countries, so a baseline 3 applies. The description reinforces the company parameter by naming the NIF alias and notes country-level outputs, but adds nothing about the 'since' cutoff or the default time window, and its use of 'countries' for outputs blurs it with the input filter.

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 opening clause 'What a company wins in public procurement' states the resource and scope precisely, and the following enumeration makes clear this is a retrospective awards/competition profile. It never explicitly contrasts itself with siblings like award_history or bid_intelligence, so an agent must infer the boundary. Clear purpose, but no sibling differentiation.

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?

'Search by name or tax id (NIF)' tells the agent how to invoke it, and the content implies the when (profiling a company's public-procurement footprint). There is no explicit when-to-use/when-not guidance and no routing to siblings such as award_history for raw award lists. Usage is implied rather than stated.

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