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

Goes well beyond the readOnly/idempotent/non-destructive annotations by disclosing rate limits (5,000 chars per call, 5 free checks/day plus a shared daily cap), data handling (text is sent to the DraftCheck service and not stored by Haven), and an important caveat that the score is a style heuristic, not authorship proof. This is exactly the kind of context annotations cannot carry.

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?

Dense but front-loaded, leading with the deprecation/alias status before the functional description. Every sentence carries information (deprecation, function, output shape, use cases, limits, disclaimer), though the volume approaches the limit for a single-parameter tool.

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?

With no output schema present, the description correctly compensates by describing the return payload (score, each tell found with location and fix hint). Combined with limits, data handling, and the heuristic disclaimer, an agent has everything needed to call this 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?

Only one parameter with 100% schema description coverage, so the schema already documents it fully. The description's 'up to 5,000 characters' matches the schema's '(<= 5000 chars)' and adds no new syntax or format detail. Baseline 3 is correct.

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+resource (scores English text 0-100 for AI-writing tells) and explicitly identifies itself as the deprecated alias of the sibling draftcheck_check. An agent can distinguish this tool from draftcheck_check and know exactly what it does.

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?

Names concrete use cases ('review a draft before publishing or to compare two versions') and signals the routing condition by stating it is a deprecated alias 'kept for existing clients', which implies new integrations should use draftcheck_check. Does not give an explicit directive like 'prefer draftcheck_check for new work', so not a full 5.

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