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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is carried structurally. The description adds genuine context beyond that: the return shape (0-100 score, verdict, per-habit examples and rationale), the scope limit "not an AI detector", and the caveat that short texts give rough scores. However, it says nothing about rate limits, latency, or handling of the 60k character ceiling, so it is a solid but not exhaustive addition over the annotations.

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 trigger phrase "Use when..." and then the return contract, which is the right order for an agent scanning for relevance. The habit enumeration in the middle sentence is long but each item is concrete evidence of what gets flagged, so it largely earns its space; only the closing rewrite note is slightly padding.

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, so the description carries the return contract itself and does so fully: score range, verdict, per-habit detail with examples and rationale, plus an important reliability caveat for short inputs. For a one-parameter read-only check, an agent has everything needed to call it and interpret the result.

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% and the single parameter already documents its 60,000-character limit, so the schema does the heavy lifting. The description's inline example {"text": "<the draft to check>"} restates the invocation shape but adds no syntax or formatting guidance beyond the schema. Baseline 3 is correct for a fully documented single-parameter tool.

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 ("check writing for AI-sounding habits") and immediately draws the boundary that matters: "It is a habit check, not an AI detector." An agent knows exactly what class of operation this is and what it produces (score, verdict, flagged habits) without opening the 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?

Explicit trigger conditions are given (user asks whether writing sounds like AI, wants an email/post/essay/cover letter checked before sending, wants phrases to fix), plus an explicit exclusion for detection and a redirect for rewriting ("use your own judgment on the flagged habits"). Nothing is left to inference.

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