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

Annotations declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is already established. The description adds meaningful behavioral context beyond annotations: it explains graceful degradation for LEI/FIGI enrichment, the fact that each call cascades through multiple lookup endpoints, and how unresolved identifiers are explicitly stated rather than omitted. It also discloses that non-ticker instruments like bonds resolve here, which is a non-obvious behavior an agent must know.

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?

The description is long but information-dense: utterance examples, supported types, source details, degradation behavior, and the acronym expansions all earn their place. It is front-loaded with the core purpose and the 'Use FIRST' instruction, and the most nuanced guidance (exact value formatting for bonds) is placed inside the parameter section where it is actionable. It could be lightly pruned, but almost every sentence adds semantic value for correct invocation.

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 read-only, idempotent resolver with 100% schema coverage and no output schema, this description is complete. It explains what each supported type returns, which sources provide the identifiers, how failures degrade, and what to pass in the value field. There is no output schema to enumerate return fields, and the description explicitly notes that unresolved identifiers are listed under 'unresolved', which is the key return-shape information an agent needs.

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 100%, so both parameters are already documented, giving a baseline of 3. The description enriches the 'value' parameter substantially by giving concrete examples (AAPL, 0000320193, 'ozempic') and the crucial warning about passing the issuer exactly as printed without trailing security-class words. The 'type' parameter is constrained by an enum, which the description also restates. This added guidance lifts it above the baseline, though the param descriptions alone already covered the basics.

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 opens with concrete natural-language utterance examples and states the core verb phrase: resolve a user-spoken NAME to the canonical/official identifiers that other tools require as input. It explicitly distinguishes the tool's job from name-recognition ('resolve a user-spoken NAME') and says to use it FIRST when you have a name but need an ID. It also names supported types and identifier sources, making it easy for an agent to choose it over siblings such as entity_profile or compare_entities.

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 gives a strong usage rule: 'Use FIRST whenever you have a name but need an ID.' It also contrasts with sibling tools indirectly by stating that this tool replaces 2-3 manual lookups and that non-equity instruments DO resolve here, which clarifies when not to assume a ticker-less name will fail. The explicit 'never the question's full noun phrase' instruction under the value parameter is practical, specific guidance that prevents a common misuse pattern.

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