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

With no annotations provided, the description carries the full burden. It conveys that this is a list-building/read operation (prospecting, market sizing), which implies non-destructive behavior, and discloses the filtering nature. However, it doesn't describe output format, pagination/limit behavior, or any rate-limit/auth constraints. For a read-oriented search tool, the disclosure is adequate but not rich.

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, zero filler, front-loaded with the core purpose first. The NAICS example is valuable but could be considered slightly tangential to the main filter list; still, it earns its place by clarifying how to use the industry filter. Efficient and well-structured.

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?

Given 9 optional parameters and no output schema, the description covers the primary use cases clearly. It would benefit from mentioning the county parameter's constraint (NY only) which is already in the schema, and from describing what a result row looks like. However, for a filtering/search tool with fully documented parameters, the description covers the essential decision-making context well.

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%, so the schema already fully documents all 9 parameters. The description adds a concrete NAICS example that enriches the semantics of the industry filter even though no explicit naics parameter appears in the schema. This example adds value beyond the schema, but much of the parameters' meaning is already in the schema, so baseline 3 is appropriate.

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 clearly states the tool 'Build a list of companies matching criteria rather than looking one up,' with a specific verb and resource. It lists the filter dimensions (state, industry/NAICS, entity type, age, city, ZIP) and explicitly distinguishes itself from a single-record lookup, differentiating it from siblings like private_entity and private_search.

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 clear when-to-use context: 'prospecting, market sizing, or finding every business of a kind in a place.' It explicitly names the alternative behavior ('rather than looking one up') and even provides a concrete NAICS usage example (23 construction, 238 specialty trades, 238160 roofing). It doesn't explicitly name a sibling tool to use instead for single lookups, but the contrast is clear. Minor deduction for not naming the alternative tool.

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