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

Annotations already establish read-only, idempotent, and non-destructive behavior, and the description adds substantial value beyond them: no re-collection, no model calls, no wallet charges, no consumption of cleaning quota, preview creates no task, and source body content is untrusted and cannot authorize actions. These are meaningful behavioral constraints not inferable from the schema or annotations.

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 description is dense and somewhat long, but the semicolon-separated workflow keeps it structured, and every clause contributes either operational sequencing, side-effect guarantees, or security guidance. Given the tool aggregates 11 sub-actions, the length is justified and there is no filler.

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?

The tool is complex—an 11-action discriminated union with no output schema—but the description covers all actions either by name or by category, adds error semantics for find_job/404, clarifies preview behavior, and warns about untrusted source data. This is sufficient for an agent to select and invoke the correct sub-action without missing critical context.

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?

The top-level schema has zero direct parameters and schema coverage is 100%, so the baseline is 4. The description adds useful semantic context, such as get_source_fields returning inferred fields without sample values, find_job using the original idempotency key, and list_recipes discovering fixed recipes, without needing to repeat schema property constraints.

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 specific read operations—get_entitlement, get_source, get_source_fields, list_jobs, find_job, list_recipes, preview, and reading existing tasks, units, results, and exports—making the verb+resource mapping explicit. It also distinguishes itself from the sibling action tool by stating what it will not do: re-collect, call models, charge wallets, consume quota, or create tasks.

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?

The description provides a concrete workflow order ('先用...再...') and action-specific guidance, such as using find_job with the original idempotency key and interpreting 404 as not-proven rather than never-submitted. It clearly implies the read-only use case, but it does not explicitly name the action sibling as the alternative for write/mutation operations.

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