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

With no annotations, the description carries the full burden and does so well: it names the categories of change (vocabulary swaps, filler stripping, em-dash reduction, significance deflation), states exclusions (protected spans), declares determinism and no LLM, and discloses that some tells are deliberately left for human judgment. This is exactly the context annotations would otherwise supply.

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 the core action and the mechanical-fix list, with the sister-tool pointer saved for last. It is dense — the long parenthetical enumerations make it run-on — but no sentence is 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?

There is no output schema, yet the description covers the return payload (rewritten text, change log, before/after ai-ness scores, residual tells list), which is the main gap a caller would otherwise have. Combined with the preservation and determinism notes, an agent knows everything needed to invoke and interpret it.

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?

Only one parameter (`text`) and schema description coverage is 100%, with the 100k character limit already documented in the schema. The description's 'POST prose' framing adds nothing beyond what the schema declares, so 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?

Opens with a specific verb+resource ('Rewrite text to remove AI-writing tells') and immediately frames the mechanism (POST prose, get it back fixed). It explicitly distinguishes itself from the sibling detector humanizer_score, so an agent can route between them without opening either 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?

The 'Sister to humanizer_score (the detector)' line implies the intended split — use this to fix, use that to measure — and the preservation rule (code fences, inline code, URLs, quotes never touched) sets a clear boundary on what input is appropriate. It stops short of explicit when-not-to-use guidance or a prerequisite like 'only for prose, not code files'.

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