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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds non-obvious behavioral context the annotations cannot convey — that the analysis is offline and therefore scoped away from SMTP-dependent checks, and that its score is not authoritative. It does not describe the shape or richness of the returned findings, which is the remaining 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, no filler. The core action comes first and the limitation plus alternative follow, with the capitalised 'IMPORTANT LIMITS' flagging the constraint an agent most needs before choosing this tool.

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-parameter read-only analysis tool with no output schema, the description covers purpose, input expectations, offline limitations, and the better alternative. The only omission is any indication of what the analysis returns or how trustworthy partial results are, which matters somewhat given the explicitly non-authoritative score.

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?

Only one parameter exists and schema coverage is 100%, so the schema already explains that the value must be the complete raw source with headers and body. The description's '(.eml source: full headers + body)' restates rather than extends that, so the baseline 3 applies.

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: 'Run a deliverability/content analysis on a raw RFC 822 email (.eml source: full headers + body).' It also names the sibling tool that gives the authoritative result, so the agent can distinguish this file-based analyzer from create_mailtest without opening either schema.

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 defines the boundary condition: 'with no live SMTP session, SPF, blacklist and reverse-DNS cannot be verified from a file' and redirects to create_mailtest 'for the authoritative score.' Both the when-not and the alternative are stated outright rather than implied.

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