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

Annotations only supply destructiveHint=false, so the description carries most of the burden and does so well: 'A human reads every message; there is no automatic reply' tells the agent to expect no programmatic response, and the consent requirement for reply_email is a real behavioral constraint. It does not describe latency, rate limits, or confirmation behavior.

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, zero filler, and the most important fact — that a human reads it and there is no auto-reply — is placed early. The reply_email caveat comes last, where it belongs.

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 4-parameter feedback tool with no output schema, the description covers purpose, routing, expected response behavior, and the consent rule. Combined with 100% schema coverage, an agent has everything needed to invoke it correctly.

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%, so the baseline is 3; the description adds value by stating the condition for including reply_email ('only if your user wants an answer'), which is a usage rule the schema's terse 'only with your user's consent' only partly implies. It adds nothing for type, message, or robot_key beyond the schema.

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 (send/tell) and resource (the convert.express team) plus the exact message categories (bug, feature, question). No sibling tool covers feedback, and an agent can immediately tell this is a human-routed feedback channel rather than a job/transcription operation.

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?

Clear when-to-use context: for bugs, missing features, or questions, and explicitly 'from you or your user'. It also gives a conditional rule for reply_email. It stops short of naming exclusions or pointing to alternatives, but the scope is unambiguous.

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