stalwart_classify_spam

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

No annotations exist, so the description carries the burden. It discloses one specific behavior—remote_ip 0.0.0.0 is rejected—but does not state whether the operation is read-only, requires authentication, or has other side effects. This leaves the safety profile partially ambiguous.

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?

The description is two sentences plus a compact bullet list of parameters. It is front-loaded with the core purpose and each parameter earns its place without fluff.

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?

Despite lacking annotations, the description fully specifies all invocation details including required vs optional parameters, defaults, and a special-case constraint. The presence of an output schema likely covers return value documentation, so the description is sufficient for correct invocation.

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?

With 0% schema description coverage, the description compensates fully by explaining each parameter: message is a full RFC 5322 message, env_from is required, remote_ip has a default and rejection note, and ehlo_domain/env_rcpt_to are marked optional. This provides meaning beyond parameter names.

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 clearly states 'Run the spam filter on a message and get the score,' which identifies a specific action and result. It is distinct from sibling tools that manage accounts, domains, queues, etc., making the purpose unambiguous.

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 description implies the tool is for checking spam classification of a message, with no overlapping sibling tools. While it doesn't explicitly name alternatives or exclusions, the unique functionality provides clear context for when to use it.

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