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

Goes well beyond the readOnly/openWorld/destructive annotations: BrokerCheck data is blocked by terms, kinds without a federal net only carry verified state guidance, and the shared seven-second budget is split across entries so slow sources may stay unavailable. It also previews the returned table's shape (dated sources, unavailable labels, limits, identity candidates), which is exactly the operational context an agent needs to set expectations.

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 usage trigger is correctly front-loaded and the closing negative list is valuable, but the long enumeration of covered industries largely duplicates the kind enum already in the schema and inflates the definition without adding selection signal.

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 comparatively complex comparison tool, the description covers the important runtime caveats (blocked sources, timeouts, no ranking) and the tool has an output schema, so return-format detail is not required. The uncovered identifiers and the exact city/state correspondence rule are the remaining minor gaps.

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?

The description conveys the semantics of entries (2-5, same kind), kind, and city/state, but does nothing for the identifier parameters (usdot, mc, crd, usda_license, cfpb_company) whose accepted forms it never explains. It also re-lists many kind values without clarifying semantics beyond the enum. With only the schema's terse property labels available, this leaves real gaps.

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?

States a specific verb (compare) plus the resource (public records) and bounds the scope: two to five businesses of the same offered kind in one city/state. This is clearly distinguishable from the single-entity siblings check_business and check_mover.

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 an explicit trigger ('when the user explicitly asks to compare') and a timing cue ('before signing or paying'), plus a clear negative list (no ranking, no winner, no booking, no money movement). It does not explicitly route the agent to check_business for the single-business case, so it stops short of naming the alternative.

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