Report the AI tells

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

With no annotations provided, the description carries the full burden and does so well: it discloses determinism, cost ("free"), locality ("nothing is uploaded"), the exact shape of each finding (rule, text, line/column, swap), the score range and scoring-version caveat, and a misuse warning. These are non-obvious behavioral traits an agent could not infer from the schema.

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 every sentence contributes — the score caveat and the version-comparison note are load-bearing. It is somewhat dense and could shed a clause or two, but there is 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?

An output schema exists, so return values need not be fully explained, yet the description still summarizes findings and the lint score usefully. Combined with the locality/determinism disclosure, an agent has nearly everything needed to call and interpret the tool 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 `text`, `dialect`, and `presets` are already documented in structured fields. The description adds no syntax or format detail beyond the schema, though it does cross-reference the `presets` tool for valid values. Baseline 3 is appropriate when the schema does the heavy lifting.

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?

Starts with a specific verb and resource: "Report the writing tells in text without changing a word." That read-only framing also implicitly separates it from `chop`, which it explicitly names as the tool that would make swaps. It never directly names a sibling it is *not*, so it falls just short of full differentiation.

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?

"Use it to find where a draft carries the patterns the profile lists, and which ones" gives clear context, and it adds an important when-not: the score "is not a reading on who wrote the text and must not be reported as one." It stops short of explicitly contrasting conditions with `drift` or `presets`, but the routing to `presets` for pack selection is present.

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