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

Annotations already cover read-only, idempotent, non-destructive and closed-world behavior, so the bar is lower. The description still adds real value beyond them: it discloses pricing ('$0.75 USDC') and the shape of the result ('an object with 21 fields including cited, contradiction_free'), which matters for a paid verdict tool. It doesn't explain what 'residue' means or how it is graded.

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?

It is short and front-loads the purpose, but the middle clause ('use it rather than `clean_json_schema` for deletion proof, not json schema') is repetitive and clumsily worded, and the pricing note is tacked on without context. Roughly one sentence's worth of waste in a three-sentence description.

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 an output schema present, the description needn't explain return values, and annotations cover the safety profile. But for a tool with nested-object inputs (`scope`, `receipts`) and a 'residue' concept that is never defined, the description leaves the agent without enough conceptual grounding on what a deletion proof is or what inputs constitute one.

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 description coverage is nominally 100%, so the baseline of 3 applies even though the description says nothing about parameters. In practice the schema descriptions are boilerplate ('See the schema for its type and whether it is required'), so the description does not compensate by explaining `scope`, `receipts`, or `subject_id`, but per rubric the schema carries this dimension.

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 opening sentence gives a specific verb+resource: 'Grade whether a deletion was executed, and report the residue', which is concrete and distinguishable from siblings. It also names the sibling it is not (`clean_json_schema`), further disambiguating. The purpose is clear despite the awkward phrasing that follows.

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?

It explicitly routes the agent away from an alternative: 'use it rather than `clean_json_schema` for deletion proof, not json schema'. That is a genuine when-to-use condition tied to a named sibling. However, the phrasing is garbled and no other conditions or prerequisites are stated.

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