read_document

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is covered. The description adds rich behavioral context: the unified interface flattening all formats to a 1D block list, the 'unit' field clarifying block semantics per format, the grade C null-text signal and how to interpret it, and the anchor-citation contract for grounding. No contradictions with 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 front-loaded with the core purpose and key behavior (anchors + range), uses bold labels and bullet-style separators for readability, and includes examples without padding. Every sentence earns its place—no fluff or repetition of schema fields.

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 an output schema exists (ReadDocumentResponse), the description doesn't need to detail return structure—it summarizes the key fields. It covers edge cases (grade C), cross-tool interactions (inspect_document, read_document_image, check_summary_grounding), and parameter semantics. For a tool with 3 params and rich sibling relationships, this is fully complete for correct invocation.

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 each parameter has a description, so the baseline is 3. The description adds practical meaning beyond the schema: it explains the block concept (via 'unit'), gives a concrete example mapping 'PDF 3~8 pages' to start=3,end=8, and clarifies that end omitted reads to a character limit. This elevates it above the baseline.

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 states a specific verb (read) and resource (document body) with a key qualifier (citation anchors), and explicitly distinguishes itself from siblings: 'inspect_document' for metadata-only needs and 'read_document_image' for grade C files. An agent can immediately tell what this tool does and why it exists.

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 gives explicit 'when to use' (reading content with anchors), 'when not to use' (inspect_document for page count/title, read_document_image for grade C), and even explains the downstream dependency on check_summary_grounding that requires anchors. This leaves zero ambiguity about selection conditions.

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