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

Discloses substantial behavior beyond the annotations: credit costs tiered by length, the free skip path, the >3,000-word background/async job flow with get_job polling, and the drift tension with polish. Annotations (non-read-only, non-idempotent) are consistent with a credit-charging mutating rewrite.

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-loads the core purpose, then layers cost, async behavior, and ordering guidance in one dense but well-ordered block. Nearly every clause carries distinct operational value, though the run-on structure could be split for readability.

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 complex tool with credit accounting, async jobs, and sibling interactions, and with no output schema, the description fully covers the return shapes (final text, before/after scores, remaining signals, or a job + status). Nothing essential 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 the baseline is 3, but the description adds real meaning — credit cost tied to text length, what force overrides, and the requirement that generation_id reference a drafted (not outline/generating) piece. It reinforces rather than merely repeats 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 precise verb+resource (iteratively rewrite text to remove measurable machine-writing tells) and names the specific mechanisms (evened-out sentence lengths, symmetric hedging). An agent can immediately distinguish it from siblings like ai_detect, polish, 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?

Gives explicit routing: when to use force, when it free-skips (<=3,000 words already clearing target), and critically how to sequence against a sibling — 'run polish FIRST and humanize last, then verify with check_voice_match'. This is richer than most definitions.

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