send_message

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

With no annotations, the description carries the full behavioral burden, and it does disclose the most safety-critical trait: dry_run defaults to true and sending requires user approval. Beyond that it says nothing about authentication requirements, how attachment_paths are resolved, or how html_body interacts with body, leaving notable gaps for a mutation tool.

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 short sentences, zero filler, with the safety-critical default front-loaded. Nothing is 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?

For a 9-parameter mutation tool with no annotations and 0% schema description coverage, the description covers only the dry_run workflow. An output schema exists so return values needn't be explained, but parameter intent and permission expectations remain undocumented.

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 0% across 9 parameters, so the description must compensate and it does not. Only dry_run is addressed (and its default is already in the schema); to, cc, bcc, subject, body, html_body, from_address, and attachment_paths get no added meaning, not even format or precedence hints.

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?

"Compose/send mail" names the resource and an action, but the paired verbs blur whether this tool only sends or also composes, and nothing distinguishes it from siblings like reply_message, forward_message, or save_draft. An agent knows the domain but must infer the boundary.

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?

It gives a real workflow rule — defaults to dry_run=true, and the actual send happens only after the user approves the preview — which is useful when-to-use context. However, it never states when to prefer this over save_draft, reply_message, or forward_message, so alternative selection is left to inference.

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