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

Goes well beyond the annotations by disclosing billing semantics (charged only on verified results, not on failure/timeout/cancel), the charge formula, the field that reports it, and the timeout fallback behavior. These are exactly the operational traits an agent needs and none are derivable from the structured fields.

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-loads the action, then billing, then idempotency, then the timeout path — a sensible priority order. It is dense but every sentence carries distinct information; the bracketed tag at the end is minor redundancy.

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?

With no output schema, the description carries the return burden and does name billing.charged_points and run_id, plus the exit path on timeout. It leaves the success-result payload shape implicit, which is a small gap for a tool that can return arbitrary skill outputs.

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 every parameter is already documented in the schema. The description adds idempotency_key behavior (repeat returns the same run), but says nothing extra about quote_id, max_cost_points, version, or wait_seconds. Baseline 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?

States a specific verb and resource ('Skill 을 실행합니다') that an agent can distinguish from get_skill_run (polling) and quote_skill (pricing). It does not explicitly name which sibling to avoid, but the function is unambiguous.

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?

Clearly explains retry semantics (same idempotency_key returns the same run rather than re-executing) and the follow-up path when the 20s wait elapses (use get_skill_run). It implies skill_id comes from search_skills via the schema, but doesn't spell out when to call quote_skill first.

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