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

The description only repeats the operation and the endpoint. Annotations state it is non-read-only, non-idempotent, non-destructive, but the caller gets no context on prerequisites (e.g., witness must be prepared first), cost/latency, or what the proof output looks like.

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 a single sentence and front-loaded, but the sentence mostly repeats the title and endpoint, which is low value.

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?

The tool is a non-idempotent write with no output schema and no annotations describing side effects. The description should explain preconditions (witness preparation), the form of the result, and whether calls are billed; none of this is present.

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 100%, so both circuitId and body are documented in the schema, and the body is deferred to the OpenAPI schema resource. The description adds nothing beyond the schema, so the baseline of 3 applies.

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?

A specific verb and resource: 'Generate a zero-knowledge proof for a circuit'. It is clearly distinguished from sibling tools like affix_circuit_verify (which presumably verifies) and affix_witness_prepare. The agent knows exactly what this tool 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?

No guidance is provided on when to use this tool versus alternatives such as affix_circuit_verify, affix_witness_prepare, or affix_proof_ref_verify. The agent must infer the correct workflow position on its own.

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