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

Annotations already declare readOnlyHint=true and openWorldHint=true. The description adds valuable behavioral context: it is passive, returns specific data categories in a defined order, and refuses certain target types. It also clarifies that results are sourced. While it doesn't mention cost or rate limits, the presence of a quote parameter in the schema partially covers that. The description goes beyond annotations by detailing the passive nature and the refusal of PII.

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 two sentences with no filler. The primary use case and scope are front-loaded, and the exclusion of people data is clearly stated. Every clause earns its place, making it efficient and easy to parse.

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 that there is no output schema, the description compensates by explaining the structure of the return (findings first, then DNS, cert, etc.) and the source attribution. It covers the passive limitation and refusal of PII. Cost is hinted at via the quote parameter in the schema. A minor gap is the lack of mention of error conditions or rate limits, but for a read-only reconnaissance tool, the description is complete enough for an agent to call it correctly.

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 coverage is 100% and both parameters (target, quote) have descriptive text. The tool description does not add new meaning beyond the schema but reinforces the accepted target types (domain, IP, URL, AS number, CVE id). This matches the schema description. Since the schema already handles parameter semantics, a baseline of 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 states a specific verb ('passive reconnaissance') and a clear resource class (domain, IP, URL, AS number, CVE id). It also lists the output categories (findings, DNS, certificate, registration, hosting, exposure facts) and explicitly excludes people-related data, making it unambiguous and distinct from the sibling tools, none of which target OSINT.

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 opens with 'Use this when you need passive reconnaissance...' and later adds 'Passive only; people (e-mails, usernames, phone numbers, names) are refused.' This conveys when to use it and when not (people-related queries are out of scope). It doesn't explicitly name alternative tools, but the sibling list contains no obvious OSINT contender, and the scope constraints are clear enough.

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