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

Annotations already cover readOnly/idempotent/non-destructive behavior, so the description's main job is adding context. It usefully reveals that the return format is HTML and that no outbound message is sent, which exceeds the annotations without contradicting them.

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 front-load the core action and add only high-value constraints. Every clause earns its place: generate a draft, return HTML, don't send anything.

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?

Given full parameter documentation, an output schema, and annotations that cover safety, the description completes the picture with the key non-obvious behavior: no message is actually sent. An agent has enough 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%, and both parameters are already well documented—item_id is identified and kind has explicit enum semantics. The description adds no parameter-specific guidance, so baseline 3 is appropriate.

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 states a concrete action—generate an AI reply draft—on a specific resource (an inbox item) and clearly frames the result as a draft for review rather than a sent message. This distinguishes it from send/accept/decline tools even without naming them.

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 establishes the right mental model: use this when you want a draft to review, not when you intend to finalize a send. It explicitly says the tool 'does not send anything,' which implicitly excludes inbox.send_reply, but it doesn't explicitly name an alternative.

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