Verify Source

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

With no annotations, the description carries full behavioral burden and succeeds: it discloses parsing of nodes, not-found and multiple-candidate handling, durable proof card contents (quote, page image, bbox focus, confidence, reasons), eager_url's single-page fetch behavior, and the API's failure rather than minting a proof without bbox. This is exceptional transparency for a complex tool.

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 long but front-loaded with purpose and organized by mode, with each sentence adding behavioral distinction. It could be trimmed slightly, but for a 16-parameter tool with no annotations, the density is appropriate.

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?

No output schema exists, yet the description compensates by describing success and reduced return states: durable proof links with quote/page image/bbox/confidence/reasons, text_match's found state without proof link, and failure behavior. It also mentions create_view integration, covering nearly all relevant aspects for a tool this complex.

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 the baseline is 3, but the description adds operational meaning beyond field descriptions: it explains mode inference when pdf_url is passed without document_id, the behavior and default of verification_requirement, and alias relationships (url, rough_pages). This raises the parameter semantics 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 opens with a specific verb+resource+outcome: 'Verify a source for a PDF-backed claim and show the result as an inline citation state card.' It also explicitly states 'This is the one model-facing source-verification tool,' distinguishing it from siblings such as verify_block and view_document.

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 clear when-to-use guidance for each mode: default auto requires document_id, eager_url is for lawfully-reachable PDFs that shouldn't be uploaded/parsed, exact_node is for when the agent is already grounded, and text_match is only for deterministic text-layer matches. It does not explicitly name exclusions versus other tools, but it strongly implies this is the sole source-verification entry point.

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