agent_models

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

With no annotations, the description carries the full burden and does well: it names the per-harness implementation paths, states that no inference is consumed, specifies the two error codes (MODEL_CATALOG_UNAVAILABLE / MODEL_CATALOG_INVALID), and guarantees no fallback to another list. It does not cover auth/permission needs for remote execution or timing/latency, so it falls short of a 5.

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?

Front-loaded with the purpose and the non-consumption guarantee, then details per-harness mechanics and error behavior. It is a dense single block rather than segmented, so some sentences are long, but each carries information that is not repeated elsewhere.

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?

An output schema exists, so return values need not be explained; the description still covers error behavior, remote scoping, and non-inference cost. Given four parameters including a nested remote object with SSH concerns, the description is close to complete, missing only notes on remote authentication expectations.

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, but the description adds real semantics beyond the schema: it explains what passing remote does (別端末のharnessの候補を返す), which the schema's remote description (SSH connection info) does not state. include_hidden's harness-specific behavior is already in the schema.

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 (取得する) and resource (harnessが今返すmodelとreasoning effortの候補), plus the authoritative source (そのharnessの公式の一覧). An agent can distinguish this catalog-lookup tool from agent_launch/agent_configure without opening any schema.

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 clarifies the alternative it is NOT (promptやturnを送らず推論を消費しない) and routes the agent onward by saying the returned id/efforts can be passed straight to agent_launch／agent_configure. No explicit 'use when X instead of Y' exclusion block, but the context of use is clear.

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