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

Annotations cover only readOnly/openWorld, so the description carries real weight and delivers: nightly refresh cadence, data-source scope, an explicit negative guarantee ('weak guesses are never returned'), and the full status vocabulary including the remediation hint for 'ambiguous'. This is behavior an agent could not infer from the schema or 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?

Front-loaded with the core question, then scope, provenance, return fields, statuses, and an example — every sentence does work. It is dense and slightly list-like in the return-field enumeration, but nothing is 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 compensates by enumerating the returned fields (entity_id, legal name, trade names, address, confidence, match_reasons) and the status enum. For a 5-param resolution tool this is complete enough to call blind.

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 the baseline is 3, but the description adds meaning the schema does not: that city/address are disambiguation levers tied to the 'ambiguous' status, plus a concrete example invocation. It stops short of explaining limit/zip interplay, so not a full 5.

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?

Opens with a specific question ('Which Texas business is this?') and precisely states the transformation: brand/trade/legal name → ranked candidates with named output fields. The Texas-only scope and the data provenance (Comptroller/TABC) distinguish it clearly from siblings like get_entity or find_affiliates.

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 actionable routing context: 'add a city or address' when status is ambiguous, and 'Pass the entity_id to the other tools' to chain into the rest of the toolset. It stops short of naming a specific alternative tool (e.g. use get_entity when you already have an ID), so it is clear context rather than explicit when/when-not.

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