prove_field_predicate

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

With no annotations, the description carries the full burden and fulfills it thoroughly: it discloses the zero-knowledge property, that the value is a witness and never persisted, that a false predicate fails locally with nothing submitted, and the immediate async return. It also adds context about scaling and contentRoot anchoring, offering a comprehensive behavioral profile.

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?

Every sentence earns its place: the first sentence states the primary function, subsequent sentences cover prerequisites, scaling, anchoring, failure behavior, and the async pattern. The description is tightly written with no fluff and is appropriately front-loaded.

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 complex 14-parameter tool with no output schema, the description covers the core aspects: purpose, prerequisites, behavioral nuances, and the return format. It could further describe error scenarios or the verification flow, but the essential operational context is complete.

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 the baseline is 3. The description adds value beyond the schema by explaining the scaled integer semantics for value and threshold, the witness-only role of value, the depth-4 Merkle path requirement for siblings/dirs, and the contentRoot anchoring behavior. This enriches the parameter understanding.

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 description opens with a specific verb phrase 'Issue a zero-knowledge field-bound predicate proof' and precisely defines the predicate as 'value <= threshold' or 'value >= threshold' while emphasizing non-revelation. It clearly differentiates from verification siblings (verify_*) by focusing on proof generation, and the singular 'field' distinguishes it from the plural sibling 'prove_field_predicates_batch'.

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?

The description provides concrete usage context: it requires the depth-4 Merkle inclusion path, explains the optional contentRoot anchoring behavior, and describes the async flow with get_job_status polling. It does not explicitly name the batch alternative or state 'when not to use', but the strong contextual detail makes the intended use unambiguous.

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