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

Annotations already cover safety (readOnly, idempotent, openWorld, non-destructive), but the description adds materially more: an external third-party dependency, a per-call cost of 8 credits, and an interpretation guide for the numeric result including the flag threshold of 30. Cost and external-service dependency are behavioral traits annotations cannot express.

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 sentences, front-loaded with the purpose, then the result semantics, then the usage condition and cost. No sentence is redundant and nothing is buried.

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, the description compensates by explaining the return scale and threshold, and it discloses cost and external dependency. For a single-parameter read-only tool, an agent has everything needed to decide and invoke 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?

There is a single parameter with 100% schema description coverage, including the minLength of 10, so the schema fully documents it. The description adds no syntax or format detail beyond that, making the baseline 3 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 and resource — check how machine-written text reads via an external AI detector — and names the exact output shape (0–65 scale with a 30 threshold). This is clearly distinguishable from siblings like humanize_text (which rewrites) and generate_social_post (which creates).

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 when-to-use: on text already written, before publishing, as a self-measurement the agent cannot perform itself. It does not, however, point to the natural follow-up sibling (humanize_text) for text that fails, nor state any exclusion, so it falls short of the explicit-alternatives bar.

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