discover_subdomains

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

Annotations already provide readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false. The description adds substantial behavior beyond those: the result is a CT sample (lower bound), unseen hosts are silently absent, a per-source `coverage` record reports what was consulted, and `countBasis` distinguishes normal reach from a recall-cut `floor`. This is exactly the kind of open-world and sampling nuance an agent needs and could not infer from annotations. No contradiction with 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?

The description is dense but front-loaded: purpose in the first sentence, use cases in the second, and the critical sampling caveat in the third. Every sentence earns its place given the tool has no output schema and needs to communicate subtle recall semantics. The final sentence packs a lot of field-level detail into one long clause, so it is not as crisp as a 5, but it is far from bloated.

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 tool with no output schema, the description is unusually complete: it covers what the result represents (a sample, not an inventory), how to interpret counts (lower bound, floor vs. normal), which fields to expect (coverage, countBasis, minSubdomainsObserved, concreteSubdomains), and the open-world limitation. The schema covers all parameters, and the annotations cover safety. Nothing an agent needs to call and interpret this tool correctly is missing.

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 all three parameters (domain, format, force_refresh) are already documented in the schema. The description adds value by explaining output semantics tied to tool behavior (coverage, countBasis, concreteSubdomains) but does not add parameter-level meaning beyond the schema. This matches the baseline 3 for high schema coverage.

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 opens with a specific verb+resource+method: 'Find subdomains of a domain using Certificate Transparency logs.' It goes further by stating the investigative use cases (shadow IT, forgotten services, unauthorized certificate issuance), which distinguishes it from siblings like check_subdomain_takeover (takeover risk) and discover_brand_domains (brand-related discovery). An agent can tell this tool apart from its siblings without opening schemas.

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 context for when to use the tool (shadow IT/reconnaissance via CT) and an explicit exclusion: 'Returns a CT SAMPLE, not an asset inventory.' This tells the agent this tool is the wrong choice when a complete asset inventory is required. However, it does not name any alternative sibling tools directly, so the routing is implied rather than explicit.

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