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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the bar is lower, yet the description still adds the decisive reassurance ('sends nothing and stores nothing') and, critically, discloses the return shape ('draft text and a mailto link') where no output schema exists. It also pins the fixed recipient address, which is behavior an agent could not infer from the schema.

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 and audience come first, and the non-mutating guarantee plus return format follow as the one fact that most affects the agent's decision. Every clause earns its place.

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?

Five parameters with only one required, full schema coverage, and no output schema, so the description's job is to explain what comes back and whether side effects occur — both are covered explicitly. Nothing an agent needs in order to call this correctly 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 each of the five properties carries its own description with examples, so the schema does the heavy lifting. The description only says the e-mail describes 'a project', adding no format, length or content guidance for `need` or the optional fields. 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 artifact ('prepare an e-mail'), names the recipient (Structomat, info@structomat.com) and the output ('ready for the user to review and send'). This is unmistakably different from the analysis siblings (analyze_frame, estimate_portal_frame_steel, get_connection), which compute rather than compose outreach.

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 makes the intended scenario clear: the user wants to describe a project to Structomat and needs a reviewable draft. It also sets a boundary on behavior ('sends nothing and stores nothing'), which tells the agent this is a safe pre-send step. It does not explicitly say when to prefer this over, say, list_services or about_structomat, so no exclusion guidance is offered.

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