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

The annotations (readOnlyHint, idempotentHint) already establish safe read-only behavior, but the description goes far beyond them. It explains the internal multi-endpoint cascade, the graceful degradation of LEI/FIGI enrichment, the 'assert nothing and return figi_candidates' behavior for ambiguous matches, and the explicit reporting of unresolved identifiers. It also discloses potential pitfalls such as the ISIN-to-LEI mapping and the bond-name caveat. No contradiction with annotations.

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 lengthy but dense with purposeful details: it covers supported types, identifier sources, matching behavior, fallback logic, and input constraints. Each sentence contributes new information without fluff. The structure flows from examples to function to type-specific nuances to degradation notes, making it easy to navigate despite its size. It could be tightened slightly, but it is not padded.

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 sufficiently describes the shape of results: labeled identifiers, an unresolved list, and figi_candidates for ambiguous matches. It also clarifies which inputs are valid and how they are interpreted (ticker, CIK, ISIN, name). Combined with the annotations, an agent has everything needed to decide whether and how to call this tool. The description is exhaustive for a tool of this complexity.

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?

While the schema already covers both parameters, the description adds substantial semantic detail that the schema omits. Notably, it introduces ISIN as an accepted input for 'value' in the company type, which the schema does not list. It also explains the impact of ambiguity (returning figi_candidates) and the exact formatting rules for bond issuer names. This goes beyond the baseline of a fully covered schema.

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 leads with concrete examples of user phrases and immediately states the core function: resolving a user-spoken name to canonical/official identifiers. It clearly enumerates supported entity types ('company', 'drug') and the specific identifier systems involved (CIK, LEI, FIGI, RxCUI), and positions itself as the first tool to use when you have a name but need an ID. This sharply distinguishes it from sibling 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 explicitly says 'Use FIRST whenever you have a name but need an ID,' establishing a crisp trigger condition. It provides a range of plausible user intents ('What's the ticker for…', 'find the CIK for…') and clarifies edge cases like bonds, where the value must be the issuer name only. While it doesn't name alternative tools, the 'FIRST' directive effectively removes ambiguity about when to invoke this tool.

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