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

No annotations are present, so the description carries the full burden. It clearly discloses a key behavioral quirk: the search matches names only, not industry classifications, with the 'roofing' example. It also notes full-text ranked search and data coverage. This is substantial behavioral context, though it doesn't detail response shape or pagination.

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?

Three sentences with no filler. The first sentence gives purpose, the second gives usage boundaries, and the third explains the name-matching caveat. It's appropriately sized for the tool's complexity, though slightly more verbose than strictly necessary.

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?

The description covers what the tool does, when to use it, and a major limitation. It lacks an explicit mention of result fields or pagination, but given the tool's simplicity, it is adequate. The reference to a potentially unavailable private_list tool is a minor gap that prevents a perfect score.

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 schema already provides full descriptions for all four parameters (100% coverage), so the baseline is 3. The description adds high-level context about ranking and name-matching but doesn't add specific syntax or format details for the parameters. It does clarify that 'state' covers 56 jurisdictions via the overall description, which is a minor enhancement.

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's opening phrase 'Find US businesses by name when you do not yet know which one you want' clearly identifies a name-search tool with a specific use case. It also distinguishes from private_resolve by contrasting browsing candidates vs. identifying a specific company. The scale (30.6M entities, 56 registries) adds specificity.

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?

Explicitly states when to use (when unsure which business, to browse candidates or check existence) and when not to use (to identify one specific company → private_resolve; for industry-based search → private_list). However, private_list is not listed as a sibling tool, which could mislead an agent if that tool doesn't exist.

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