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

Annotations already declare readOnly/idempotent/closed-world, and the description still adds real context: offline operation with no URL fetching, no account or token, a 1 s analysis budget, not a compliance certification, a redaction warning, and the abstention behavior when nothing is proven.

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?

Front-loaded with the core action, then clearly delimited When-to-use and Notes sections; the example arguments block is verbose because of the escaped trace text but is genuinely functional, not padding.

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?

Return values are documented by the output schema, and the description supplies everything else an agent needs: input formats, limits, cost/account requirements, abstention semantics, and a data-handling warning.

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%, so baseline is 3, but the example arguments add meaning by showing the exact trace paste format and how the optional question is phrased; the description's 'paste the trace' instruction reinforces the trace parameter's intent 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?

States a concrete verb+resource ('Analyze an HTTP request/response trace') plus supported input formats and offline behavior, and the scope is clearly distinct from siblings like check_web_support and get_rfc_status.

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 'When to use' paragraph names concrete debugging scenarios (caching, conditional requests, Content-Length/Transfer-Encoding, 304/204/HEAD) and clarifies it never fetches URLs — you paste the trace. It lacks an explicit pointer to which sibling to use for adjacent needs, which keeps it below 5.

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