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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and openWorldHint=false, and the description reinforces the offline nature with 'Text only: nothing is looked up or stored.' More importantly, with no output schema present, it discloses exactly what the response contains: verdicts, alignment reasoning, relay hops and delays, sending IP, plain-English issues, and RFC 8058 List-Unsubscribe evaluation.

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?

One sentence, front-loaded with the action ('Read a received message's raw headers'), followed by the return payload. Every clause carries distinct information and the closing constraint is placed last for emphasis; no filler.

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, no-output-schema tool, the description covers the safety profile via annotations and enumerates the returned fields thoroughly, so an agent knows what to expect back. Nothing material for correct invocation 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% and the single parameter is fully documented there (raw header block, Gmail 'Show original' hint). The description adds only the 'received message' qualifier, not new format or edge-case guidance beyond the schema. Baseline 3 applies when the schema does the heavy lifting.

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 and resource: 'Read a received message's raw headers', and enumerates the verdicts returned (SPF/DKIM/DMARC as recorded by the receiver, alignment, hops, sending IP). It implicitly separates itself from DNS-checking siblings by stressing 'receiver recorded' and 'nothing is looked up', but never names the closest alternative (analyze_microsoft_headers) or any sibling explicitly.

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 scope ('a received message's raw headers') and a concrete use case ('why DMARC failed on a message that passed') imply when to reach for it, and 'nothing is looked up' hints that check_dkim/check_spf/check_email_authentication serve a different purpose. However, there is no explicit when-to-use/when-not or named alternative, so routing must be inferred.

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