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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is largely covered. The description still adds real operational context beyond them: a cost ceiling ('8 units') and an auth requirement ('API key required'). It stops short of richer behavior like latency, caching, or whether the report is persisted, so it is not 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-loaded with the core verb and payload, then cleanly segmented into usage, exclusion, Inputs, Returns, and Limits lines. Dense but every clause carries information, with no filler or restated title.

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?

An output schema exists, yet the description still names the top-level return fields (company, facts, links, decisions, changes_last_year, modules, gaps, uncertainty, sha256, markdown), plus the two parameters, the usage boundary, the cost limit and the auth requirement. Nothing an agent needs to decide or invoke is missing.

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% and both parameters are documented inline (enum values, SIREN/SIRET/VAT formats, examples). The description only adds a cross-reference that the inputs work 'as lookup_company' with the same format — marginal added meaning, so the baseline 3 applies.

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 ('Produce one review-ready report on a company') and enumerates the report's contents (identity, facts with sources, changes, all checks at once). It explicitly distinguishes itself from siblings by naming lookup_company as the alternative for a single fact, so an agent can route without opening 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?

Gives explicit when-to-use ('registry part of a KYB or supplier review you must file'), explicit exclusions ('not full KYB: no UBO, PEP or adverse-media checks'), and an explicit alternative with its triggering condition ('Don't use it for one quick fact: call lookup_company'). Both the positive and negative cases are covered.

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