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

With no annotations, the description carries the full burden and does meaningful work: it discloses the cost model (free up to 5000 chars) and the return shape (a score plus each tell with location and fix hint). It omits auth requirements, rate limits, and what happens past the 5000-char boundary, which keeps it below a 5.

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?

Three short sentences with the pricing/limit constraint front-loaded, then purpose, then usage. Every clause earns its place and nothing is 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?

Given no output schema, no annotations, and one parameter, the description covers the essentials: input limit, what is returned (score, tells, locations, fix hints), and when to invoke it. It leaves open the score's range/meaning and how it differs from slop_patterns.

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?

The single 'text' parameter has no schema description (0% coverage), so the description must compensate. It does so by framing the input as a 'draft' and imposing a concrete 5000-char limit, which is real semantic information about the parameter even if format expectations remain vague.

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 and resource: score a draft for AI-writing tells and list each tell with location and fix hint, which is far more concrete than the name alone. It differentiates itself from slop_check_long only implicitly via the '5000 chars' cap and gives no clue about slop_patterns, so sibling separation is partial.

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 a clear usage context ('Use before publishing any text you generated') and an implicit boundary condition (up to 5000 chars) that routes longer drafts elsewhere. It never names an alternative tool or states an exclusion explicitly, so it stops short of full when/when-not guidance.

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