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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds beyond that by noting 'requires no API key; rate-limited' and specifying that the output is a text report rather than a structured JSON object. This enriches the behavioral picture without contradicting 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?

Four sentences, each with a distinct job: core function, intended use case, sibling differentiation, and input/output contract. The description is front-loaded and avoids redundancy, though it is slightly longer than the minimal two-sentence ideal; no sentence feels wasted.

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?

With only one required parameter, an output schema present, and detailed annotations, the description covers all needed context: input format, output format, intended use, alternative tool, and operational constraints. Nothing an agent needs to select and invoke 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%: the input schema already explains exactly what 'headers' should contain, how to copy it, and what to exclude. The description only restates 'INPUT is the full raw header block,' adding no new parameter semantics beyond the schema. Baseline 3 is appropriate given the 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 states a specific verb and resource: 'Parse raw email headers to reconstruct the delivery path... extract SPF/DKIM/DMARC... measure per-hop delays, and flag unencrypted hops.' It clearly enumerates the tool's outputs and distinguishes it from the sibling email_auth by specifying a different diagnostic use case.

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?

Explicitly states when to use the tool: 'diagnose a specific message that was already delivered — spoofing, delays, or where mail was lost.' It also names the alternative: 'Use email_auth instead to assess a domain's sending configuration before sending,' and adds operational guidance about being read-only, keyless, and rate-limited.

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