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

Annotations already declare destructive/idempotent/openWorld, but the description adds substantial context beyond them: account-level 5 RPM, concurrency 5, daily 1,000 and first-period 30,000 unit caps; cleanup does not deduct wallet funds; the task is executed asynchronously by the server; and delete_result makes the body immediately unreadable. The idempotency retry prohibition and the explicit permission requirement for the activate key are also operational details the annotations cannot convey.

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?

Content is dense with substance and nothing is obviously filler, but it is delivered as a single undifferentiated paragraph mixing Chinese and English, so the four distinct action branches are not structurally separated. For a four-action tool this hurts scanability, even if the length itself is defensible.

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 a complex oneOf-discriminated multi-action tool with rich annotations and no output schema, the description covers the activation gate, submit input restrictions, retry/idempotency rules, rate limits, billing non-impact, and the destructive effect of delete_result. It is largely complete; minor gaps remain around what cancel does and what the successful submit/activate responses contain.

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 baseline is 3, but the description adds real constraint meaning: submit accepts only recipe/source/version/selected_fields/options plus a stable idempotency_key and rejects arbitrary prompt, model, tools, or URL. It also ties policy_version and confirm_activation semantics to activate, going beyond the raw schema types.

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 enumerates the four concrete operations (activate, submit a fixed-recipe cleanup, cancel a job, delete a result) with a specific verb+resource for each, so an agent can tell what the tool does. It does not name the sibling `everyinfra_data_cleanup_read` directly, though '查询不自动激活' and '先读原任务' gesture at it, so sibling differentiation is only implicit.

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 gives real when-to-use conditions: activate requires explicit user confirmation plus the current policy_version, submit is scoped to the caller's own EveryData collection results, and queries never auto-activate. It also prescribes retry behavior ('超时或 unknown 不得换幂等键重发；先读原任务'), which is genuine usage guidance, though it never names the read sibling explicitly as the alternative.

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