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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, so safety is covered. The description goes far beyond annotations by explaining graceful degradation ('LEI/FIGI enrichment degrades gracefully'), internal cascading ('Each call cascades through several lookup endpoints internally'), how ambiguity is handled (returns `figi_candidates` instead of asserting), and explicit unresolved fields. It also discloses that every identifier is source-labelled. This is rich behavioral context that the annotations do not provide.

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 every sentence carries essential information for correct invocation. It starts with natural-language triggers, then specifies supported types and their resolution logic, covers edge cases, and ends with a note about replacing manual lookups. Front-loaded with the most critical usage guidance ('Use FIRST'). While dense, it avoids fluff; the length is warranted by the complexity of the tool. A thorough agent would benefit from all details.

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 must convey what the tool returns. It does: mentions `figi_candidates` for ambiguous matches, `unresolved` for failed identifiers, source-labelled identifiers, and specifics for each type (CIK, ticker, LEI, FIGI, RxCUI, ingredient, brand). It also covers input constraints (e.g., 'exactly as printed' for bond issuers). The description is comprehensive enough for an agent to confidently call the tool and interpret results, including error/fallback behavior.

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% (both type and value have descriptions). The description adds extra value beyond the schema: for the `value` parameter, it provides explicit instruction to pass the ENTITY NAME ONLY, with a concrete example of a bond issuer and what to omit. It also clarifies type-specific behavior (e.g., ISIN resolves to legal entity via GLEIF). This enriches the schema's basic descriptions, justifying a score above the baseline of 3.

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 explicitly states the tool resolves user-spoken names to canonical/official identifiers needed by other tools, and enumerates supported types ('company', 'drug') with specific identifier outputs. It distinguishes itself from siblings by framing it as the 'first' tool to use when converting a name to an ID, and it clarifies what it does not do (e.g., asserting on ambiguous names). This is a specific verb ('resolve'), a clear resource (identifiers), and enough detail to differentiate from tools like 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 strong guidance on when to use the tool: 'Use FIRST whenever you have a name but need an ID.' It also provides examples of natural-language phrases that trigger it. However, it does not explicitly mention alternative tools or when NOT to use it beyond the ambiguity case. It implies exclusion by saying 'other tools require as input,' but does not name siblings like entity_profile or compare_entities. The 'when' is explicit, but the 'when-not/alternatives' is only implicit.

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