Audit a draft

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

With no annotations, the description carries the full behavioral burden. It clearly states what the tool scans, what it returns (suggested fixes), and a behavioral boundary (never rewrites). It does not specify the exact shape of the suggestions or explicitly note read-only status, but 'never rewrites' sufficiently communicates non-destructive intent for a simple audit tool.

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?

One tightly written sentence packs in the tool's purpose, the full list of what it detects, the output type, and its key limitation. The parenthetical list is specific but not bloated, and the key 'never rewrites' distinction is placed at the end for emphasis.

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 one-parameter tool with no output schema, the description adequately explains the input, the detection criteria, and the kind of result to expect. The only minor gap is that the format of the suggested fixes is not described, though the main usage scenario is clear without 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?

Schema coverage is 0% and the only parameter, text, is minimally described. The description compensates by calling the input 'a draft,' but it stops short of clarifying input constraints, format expectations, or edge cases. For a single self-descriptive parameter, this is acceptable but not richly elaborated.

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?

The description identifies a specific verb ('Scans') and resource ('a draft') and enumerates the exact AI tells it detects: inflated claims, formulaic structure, em-dash overuse, chatbot phrasing, robotic rhythm. It also draws a clear line from sibling editing tools by stating it 'never rewrites'.

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 description communicates when to use this tool: to audit a draft for AI tells and get suggested fixes. The phrase 'never rewrites' implies it should not be used when a rewrite is needed, and the sibling edit_post is the natural alternative, though it is not named explicitly.

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