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

Annotations already declare readOnly, idempotent, non-destructive, so the safety profile is covered. The description adds useful behavior beyond that: the checks are against Gmail/Yahoo bulk-sender rules, and any body included with the headers is ignored. It does not mention whether any live DNS/network lookups occur despite openWorldHint, a minor gap.

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?

Two sentences, front-loaded with the action and an enumerated checklist, followed by the one operational note that matters. No filler or restatement of the title.

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 single-input, read-only checker with no output schema, the definition covers what is validated and how to supply input correctly. It stops short of indicating the result shape (per-check pass/fail versus a summary), which an agent might want but can discover at call time.

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 the single parameter is well documented. The description adds real value beyond the schema by specifying the expected form of the input — raw headers as the recipient received them, with a concrete Gmail path to obtain them — which reduces malformed input.

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 specific verb (check) and resource (a received email's headers) and enumerates exactly what is validated: SPF, DKIM/DMARC, alignment, one-click unsubscribe, TLS, rDNS, Message-ID. The focus on a received message's raw headers clearly separates it from check_domain and check_sending_ip, which operate on a domain or IP.

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?

Gives a concrete acquisition instruction — use the full headers as the recipient got them, with the Gmail 'Show original' pointer — which is the key prerequisite for correct invocation. It does not explicitly say when to prefer check_domain or check_sending_ip, so alternatives are left implicit.

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