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

Annotations only declare the safety profile (non-readonly, non-destructive, non-idempotent), so the description carries most of the burden and does it well: credit costs by word band, free skipped:true path, 3-pass cap, background processing over 3,000 words with status 'processing' and a get_job follow-up, and save semantics. It stops short of describing the delta/return structure, but coverage is otherwise rich.

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?

Long but densely packed and front-loaded with the core mechanism before edge cases and costs. Nearly every sentence carries operational detail (statuses, credits, job flow, humanize ordering); it is verbose but not padded.

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 multi-mode, paid, potentially asynchronous tool with no output schema, the description covers modes, prerequisites, cost, async return path, persistence, and the sibling-ordering constraint — everything an agent needs 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 coverage is 100%, so the baseline is 3, but the description adds real value: it clarifies the two mutually exclusive modes (text + profile_id vs generation_id, with generation_id 'preferred'), notes save only applies in generation_id mode, and restates the default target of 0.9 beyond the schema's minimum/maximum.

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 (auto-polish) and resource (draft) with a precise target mechanism: measured against a profile, divergences drive revision, re-measured up to 3 passes. This clearly distinguishes it from siblings like humanize, generate_content, and check_voice_match.

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 when to use it ('after generate_content when the score falls short, or on any text with profile_id + text') and states the prerequisite status ('drafted' or 'edited') plus the failure mode ('outline' returns no_draft). It also resolves the ordering tension with humanize.

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