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

Annotations already cover the safe-read profile, yet the description adds substantial context: setup_required means no store app is connected (tell the user to open the error link, don't report zero reviews) and syncing means first sync is running. It also flags that draft text may quote untrusted review text — a prompt-injection warning beyond any structured field.

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?

Front-loaded with what the tool returns, then use cases, an example payload, and error-state semantics — each sentence carries distinct information with no filler.

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?

Output schema exists so return values need no explanation; the description still covers pagination via next_cursor, downstream draft_id usage, and the setup_required/syncing states. Nothing needed to call it 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 coverage is 100%, so limit, app_id and cursor are already documented. The description only adds a worked example, not syntax or filtering semantics beyond the schema. 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 resource with useful qualifiers: unsent reply drafts, AI or hand-written, ordered newest first, in Review Expert. An agent can distinguish it from review-reading siblings like get_app_reviews. It does not name an explicit alternative, but the resource 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?

Explicitly says to use it to review pending drafts or to obtain a draft_id for delete_draft, which routes the agent to the right downstream tool. No when-not-to-use exclusions, but the use context is clear.

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