Annotate PDF (markup / drawing)

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

Beyond annotations (idempotentHint, non-destructive), the description adds key behavioral details: non-destructive incremental update, byte-for-byte preservation, appending to /Annots, and rejection of encrypted sources. No contradictions.

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 concise (4-5 sentences) and well-structured: purpose, incremental update, types, parameter guidance, and caveat. Every sentence earns its place with no redundancy.

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 complexity (multiple annotation types, many optional parameters), the description covers the core functionality, constraints, and edge cases (encrypted source rejection). Output schema exists, so return value explanation is unnecessary.

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 description clarifies parameter usage beyond schema: explains required fields per annotation type (e.g., line needs start/end), clarifies 0-based page and rect format, and lists type-specific optional fields. Adds value despite 50% schema coverage.

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 tool adds markup/drawing annotations to an existing PDF, specifying the action, resource, and annotation types. It distinguishes from siblings like add_attachment or extract_text by focusing on visual overlays.

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 explicitly notes that annotations are non-destructive visual overlays that do not remove or redact content, and that encrypted sources are rejected. This provides clear when-not-to-use guidance, though it lacks explicit alternative tool names.

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