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

Annotations already state readOnlyHint=false and idempotentHint=false, so the write-ish, non-idempotent nature is covered structurally. The description adds only the HTTP endpoint, disclosing nothing about what the prepared witness is, whether it is persisted or returned, its lifetime, or any auth requirements — thin even against the lowered annotated bar.

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?

A single front-loaded sentence that names the action, the artifact, and the endpoint with no filler. It is well-structured, though brevity here shades into under-specification rather than tightness.

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?

For a non-idempotent POST into a complex cryptographic workflow, with no output schema and an opaque request body, the description leaves too much open: no input contract, no indication of the return artifact, and no pipeline context relative to the many affix_circuit_* and affix_proof_* siblings.

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 one parameter ('body') whose schema description merely delegates to an external 'AffixIO OpenAPI schema resource' rather than documenting the contract. The nominal 100% coverage is therefore uninformative, and the prose adds nothing about the expected body shape for a POST endpoint.

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 ('Prepare a witness') tied to a concrete domain object ('zero-knowledge circuit proof'), which an agent can distinguish from a bare 'witness' tool. It does not, however, differentiate itself from nearby siblings such as affix_circuit_prove or affix_circuit_verify, so the agent must infer where witness preparation sits in the proof pipeline.

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?

There is no when-to-use guidance, no statement of prerequisites (circuit id, inputs), and no mention of the sibling tools that consume or produce the witness. The description only says what the call is, not when to reach for it over affix_circuit_prove.

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