search_installations

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

With no annotations provided, the description carries the full behavioral burden and does so richly: it discloses the return shape and ordering (largest first), the total-count field, privacy redactions ('[name withheld: possible natural person]', suppressed city/LEI, lei_withheld), the fact that no account-holder names are stored, and that registry text is wrapped as untrusted remote text to defend against prompt injection.

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-loaded with the core purpose, and every clause carries information (filters, result fields, ordering, count, privacy, injection wrapping). It is dense and the second half is one very long sentence, which slightly hurts scannability, but little of it is 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 search tool with no output schema and no annotations, the description is complete: it lists the returned fields, ordering, count semantics, filtering behavior, and privacy handling. An agent has everything needed to call it and interpret results 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 coverage is 75% and the schema already documents country and activity codes in detail, but the description adds beyond it: query requires all words to match with accents/case ignored, limit defaults to 20 (schema only has min/max), and it restates the activity/country filter semantics. This is more than the schema alone conveys, though it does not fully document every edge case.

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 (Find) and precise resource set (EU ETS installations, aircraft operators, shipping companies in the Union Registry snapshot) plus the search fields. This immediately distinguishes it from siblings like dataset_info, installation_history, company_by_lei and top_emitters, which are lookup/history/ranking tools rather than text 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 explains the search conditions (all words must match, optional country/activity filters) and the schema notes query may be empty when a filter is supplied, which implies usage. However, it never names an alternative sibling or states when NOT to use this tool (e.g. for a single known installation_id or LEI, where company_by_lei or installation_history would be better).

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