查询生成进度

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

The annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds genuinely new behavioral context beyond that: found=false means the history is temporarily missing, and succeeded must be read from native status rather than guessed from a URL. It does not explain polling or refresh behavior, which is a minor gap.

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 definition is one compact sentence with the core action first, followed by the two interpretation caveats. Nothing is wasted, though the density of semicolon-separated clauses makes it slightly terse to parse.

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 structure need not be documented, yet the description still explains the meaning of the found and succeeded fields, which is exactly the semantic layer the schema cannot carry. The only missing piece is what the agent should do after encountering found=false, which the description mentions but does not resolve.

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% for the single task_id parameter. The phrase 'real task ID' adds a small but useful constraint that the ID must be an actual task identifier, but it does not give a format, an example, or where to obtain the ID, so it only partly compensates for the empty schema description.

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 states a specific verb and resource: query native progress by real task ID. It distinguishes this lookup from mutation siblings such as pavo_submit_task, but it never names the closest alternative (pavo_get_operation or pavo_sync_task_result) by name.

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 by 'query native progress by real task ID' and reinforced by the warning about found=false. There is no explicit statement of when to prefer this over sibling tools such as pavo_get_operation or pavo_sync_task_result, so the agent must infer the choice.

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