kev_permute

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

With no annotations, the description carries the full burden. It discloses key constraints: state can be any JSON value, questions must contain exactly one choice question, n_perm is 1-64, and seed controls reproducibility. However, it does not describe what the tool returns, whether it mutates state, or how errors/invalid input are handled.

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?

The description is compact and front-loaded with the main purpose. The parameter constraints are packed into two later sentences without unnecessary filler. It could be slightly more structured, but every sentence earns its place.

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?

Given that an output schema exists and the description fully explains the parameters and input constraints, an agent has enough to invoke the tool correctly. The only real gap is lack of explicit behavioral details about output/error cases, but the output schema mitigates that.

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 0%, but the description compensates thoroughly. It explains that state accepts any JSON value, questions must be an object with exactly one choice question of the specified shape, question must be that question's key, n_perm is bounded 1-64, and seed controls reproducibility. This gives meaningful semantics for all five parameters.

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 uses a specific verb ('Evaluate') and resource ('one Choice question under multiple option orders') and states the goal ('check order sensitivity'). It clearly indicates this is a specialization of evaluation, though it does not explicitly name sibling alternatives like kev_evaluate.

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?

Usage is implied: this tool exists for testing order sensitivity of a Choice question. However, the description does not explicitly say when to prefer this over kev_evaluate or kev_separate, nor does it state any exclusions, so the agent must infer the boundary from the sibling names.

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