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

The annotations already signal that this is read-only, idempotent, and non-destructive, so the behavioral burden on the description is lower. The description adds one useful fact: classification relies on a 'loaded curated company profile set,' implying offline/predefined data rather than live enrichment. It does not disclose behavior for unknown domains, output structure, or fallback semantics, but the annotations carry much of the safety profile.

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 a single, front-loaded sentence that starts with the action verb and object. There is no redundant filler, though the phrase 'loaded curated company profile set' is somewhat vague. It is concise without being overly skeletal.

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 one-parameter tool, the schema covers the input and the annotations cover safety, so the description does not need to be long. However, with no output schema, the description's failure to define what 'classify' returns leaves the agent uncertain about the result format or categories. The absence of any pointer to sibling tools also weakens completeness.

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 fully documents the single 'url' parameter with an example ('nvidia.com'), so schema coverage is 100%. The description's 'domain' wording simply reinforces the schema rather than adding new normalization, formatting, or validation semantics. A baseline of 3 is appropriate because the description adds no meaningful parameter-level detail beyond the 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 states a clear verb and object ('Classify a domain'), making it easy to identify as a classification tool. However, it does not specify what classification result is returned or how it differs from sibling tools like company_industry or company_enrich. It is clear but not fully specific.

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?

There is no guidance on when to use company_classify versus alternatives such as company_search, company_industry, company_signal, or company_enrich. The phrase 'using the loaded curated company profile set' hints at a conditional data source but does not state when this tool should be preferred. The agent is left to infer usage context.

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