PDF一键救援

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

No annotations are provided, so the description carries the full transparency burden. It discloses automatic diagnosis/planning, selection of foreground vs recoverable background execution based on document type and estimated time, and real-time per-page progress updates. It does not mention failure modes or side effects, but it goes well beyond a generic statement of purpose.

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 compact and front-loaded with the most important directive (preferred entry point, don't force user to choose internal tools). It uses four sentences with no repetition of schema details, and every clause adds functional information. This is excellent for an 11-parameter orchestrator.

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 the high complexity (11 parameters, multiple workflows, many sibling tools) and the existence of an output schema, the description covers the main invocation pattern, automatic workflow selection, foreground/background behavior, progress reporting, and the ability to query status/QC/resume/evidence through the same entry. It does not enumerate every workflow enum, but those are already described in the schema.

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%, and every parameter already has a descriptive schema entry, so the baseline is 3. The description adds minimal value by reinforcing that path and request are the primary inputs and job_dir is for existing tasks, which is already evident from the schema. It does not significantly deepen parameter understanding beyond the schema.

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 explicitly names rescue_pdf as the preferred entry point ('首选入口') for single-PDF requests, with concrete actions: diagnose, plan, extract foreground/background, and query progress/QC/resume/evidence. It also differentiates from sibling tools by instructing the agent not to make the user select internal tools, making the orchestrator role unmistakable.

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 clearly states when to use: for direct user requests about a single PDF, passing the path and raw request, and also for querying existing tasks via job_dir. It lacks explicit exclusions (e.g., batch/library scanning) and does not name alternative siblings, but the primary usage context is strong and actionable.

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