async_job

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

With no annotations, the description carries the full burden. It usefully discloses 'Read-only except cancel,' clarifying that three of four actions are non-mutating. However, it doesn't say what cancel does to stored results (destructive? reversible?), nor permissions or timing behavior for status polling.

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?

One dense sentence with the resource and provenance front-loaded and the read-only caveat at the end. No filler; every clause 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?

For a two-parameter tool with full schema coverage and no output schema, the description covers origin, actions, and mutation caveat adequately. Minor gap: no mention of how 'list' behaves (scope/pagination) or how long results are retained.

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 coverage is 100%, so both jobId and the action enum are fully documented in the schema. The description adds no parameter meaning beyond the schema's own text, so 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 specific verbs (poll/cancel) and resource (background jobs) and names the exact origins of those jobs (media_extractor batch_extract, see_page steps, execute_js). An agent can distinguish this from siblings like wait or get_content without opening the 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?

Clearly scopes usage to jobs created with async:true on three named tools, which is a strong selection signal. It stops short of explicitly contrasting with the sibling 'wait' (i.e., when to poll vs. block) or stating exclusions.

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