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

Annotations declare this is a mutating, non-idempotent, non-destructive operation; the description adds the crucial consequence that approval does NOT publish — it only queues the text — and that rejection is a skip, not a delete. This meaningfully extends what the annotations convey. It does not clarify repeat-call behavior, which idempotentHint=false implies but doesn't explain.

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?

Three short sentences, no filler. The core action leads, the state-changing consequence follows, and the guardrail ('Act only on the user's decision') closes. Every sentence 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?

For a three-parameter mutation with no output schema, the description covers the side effect of each enum branch, which is the main risk an agent could get wrong. It leaves unstated whether the pending reply remains visible afterward and where the resulting draft can be inspected, minor gaps given list_drafts is already named.

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 reply_id, action, and edited_text are already documented (including the edit-only requirement and the 2000-char cap). The description restates the action outcome but adds no syntax or format detail beyond the schema. Baseline 3 applies when the schema carries the parameter burden.

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 opens with a precise verb triple and a clearly scoped resource: 'Approve, edit or reject one pending AI-drafted reply.' This separates it cleanly from sibling tools like generate_persona_reply (generation) and list_persona_replies (listing), so an agent can route correctly without opening any schema.

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 clear operational context: approval/edit results go to the draft queue (naming list_drafts), rejection marks skipped, and 'Act only on the user's decision' sets the trigger condition. It stops short of explicitly contrasting itself with review_drafts, so the when-not alternative 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.