grade_pdf

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

No annotations are provided, so the description must carry the full burden. It mentions the output path and confidence tier, but does not disclose side effects such as file overwriting, permissions required, or error behavior. This is insufficient for a tool that writes files.

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?

A single sentence conveys the core purpose without any wasted words. It is front-loaded with the essential action and result.

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 description explains the output location and that it includes a confidence tier, but lacks details on return values (no output schema), error handling, or idempotency. Given the tool writes a file, more context on side effects and success criteria would improve completeness.

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 each parameter is already documented. The description adds context about the output file pattern and confidence tier, but does not provide additional parameter-specific meaning beyond what the schema offers. Baseline of 3 is appropriate.

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 clearly states the action ('OCR'), the resource ('single hand-written answer PDF'), and the output ('into answers/converted/<stem>.md with a confidence tier'). It is specific and distinguishes from siblings like ingest_pdfs which likely handles multiple PDFs.

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 implies usage for a single PDF, but does not explicitly state when to use this tool vs alternatives (e.g., ingest_pdfs for batch processing). No guidance on prerequisites or exclusions.

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