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

Annotations declare openWorld and non-destructive but not the human consequences; the description adds them — a confirmation email goes to the person and the team replies in 2 to 8 business hours. It does not warn about duplicate submissions or what happens on failure, which matters given idempotentHint=false.

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 dense sentences, front-loaded with purpose followed by guardrails and expected outcome. No filler or repetition of schema details.

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 an 8-parameter, non-idempotent, open-world send tool with no output schema, the description covers intent, consent, and expected follow-up well. It stops short of describing the immediate return value or error behavior (invalid email, rate limits), which an agent would need to recover from failures.

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 coverage is 100%, so baseline is 3, but the description adds meaning the schema lacks: the 'confirmed' flag is tied to showing the person the message first, and the message should be 'in their words'. That clarifies the semantic contract rather than restating field types.

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: sends a project inquiry or question to the Developh team on behalf of the person being helped. None of the siblings (list_case_studies, run_website_audit, studio_info) do this, so the routing is 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?

Gives an explicit precondition ('only when the person explicitly asked to contact Developh and gave you their own name and email'), an explicit prohibition ('never invent or guess contact details'), and a procedural rule ('show them the message before sending'). An agent knows exactly when this applies and when it does not.

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