start_reference_check

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

Annotations indicate readOnlyHint=false and openWorldHint=true. The description goes well beyond by detailing the three-phase workflow, auto-approve option, cost implications, and expected outputs (XLSX, viewer URL, metadata). It explains the approval gate and how wait_for_job interacts with phases, providing rich behavioral context.

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 well-structured with clear sections for inline text, file upload, and phases. It is informative but slightly lengthy; some details like the exact return of upload_file could be omitted. Overall, it is organized and front-loaded with key purpose.

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 tool's multi-phase complexity, the description covers all essential aspects: input formats, phase details, approval gate, auto-approve, output types, and links to other tools (upload_file, wait_for_job, approve_validation). The output schema exists to cover return values, so completeness is excellent.

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% with clear descriptions for all three parameters. The description adds value by explaining the mutual exclusivity of text and s3_key, and clarifying the behavior of auto_approve. However, most parameter meaning is already in the schema, so the description enhances rather than replaces.

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 submits a reference-check job to fact-check text or documents. It distinguishes itself from sibling tool start_table_validation by explicitly stating not to use that for PDFs, and provides two input modes: inline text or S3 key of an uploaded file.

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 provides explicit when-to-use guidance: for fact-checking text with 4+ claims, and when not to use: fewer claims may produce low-quality results. It also warns against using start_table_validation for PDFs, naming an alternative tool.

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