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

Annotations already establish readOnly/idempotent/non-destructive/open-world, so the bar is lower, and the description still adds real context: local check-digit verification of the LEI before any call, ranked (not exact) name matching, inclusion of parent-chain data, and a CC0 data license. It does not describe what happens on an invalid LEI or empty result set, keeping this from 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?

A single dense sentence, but front-loaded with the agent-relevant question 'Who is this legal entity?' followed immediately by the data source and the two input modes. The trailing output-field list and license tag are useful rather than wasteful, though the enumeration is long enough to border on inventory.

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?

There is no output schema, so the description correctly carries the return-value burden by listing the record fields. Annotations cover the safety profile, and the parent/CC0 details round it out. Missing only edge-case behavior (invalid LEI, no matches, how many candidates limit defaults to) to be fully complete.

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 50% – lei and name are documented in the schema, while limit and parents are bare. The description partially compensates by naming 'direct and ultimate parents' (mapping to the parents flag) and 'ranked candidates' (mapping to limit), but never ties those phrases to the parameters or explains what limit=1 vs 10 changes. Baseline 3 is appropriate.

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?

Names a specific resource (GLEIF LEI record) and enumerates exactly what comes back: legal name, jurisdiction, legal form, status, addresses, registration/renewal, direct and ultimate parents. It also states the two lookup modes (by 20-char LEI or by name), which distinguishes it from name-free siblings. It stops short of naming a sibling it should be preferred over (e.g. company_lookup), so it is clear but not fully differentiated.

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 'or' construction implies the two mutually exclusive entry paths that the schema's anyOf enforces, and 'ranked candidates' signals that name search is fuzzy rather than exact. There is no explicit when-to-use statement versus company_lookup or sanctions_screen, and no stated failure/precondition behavior, so usage is implied rather than guided.

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