FactCheck — Validate

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It explains that the tool fetches code evidence and returns it for assessment, and it imposes a critical constraint on relying only on this tool's output. This goes beyond the schema and gives the AI a clear mental model of the tool's behavior, though it does not explicitly state non-destructiveness or error handling.

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 and front-loaded. The first sentence states the core purpose, the second provides usage instructions, and the third delivers an essential warning. Every sentence earns its place with no filler.

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 tool has no output schema, so the description must convey return behavior. It does so by stating that the tool returns code evidence alongside each claim for assessment. It also lists available repositories, which is critical for correct invocation. While it doesn't address edge cases like missing code, the core context needed for use is covered sufficiently.

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 description coverage is 100%, with detailed descriptions for `items` and `document`. The description adds minimal semantic value beyond the schema, essentially restating that each item requires claim text, repository, keywords, or file paths. This does not meaningfully improve agent understanding beyond what the schema already provides.

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's purpose: 'Stage 2 of fact-checking: retrieves actual code evidence for each validation item and returns it for you (the AI) to judge.' It uses specific verbs ('retrieves', 'returns') and distinguishes itself from siblings like `factcheck` (stage 1) and `query`/`suggestion` (NotebookLM tools).

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 usage guidance: 'Call this after `factcheck` has helped you identify items to validate.' It also includes strong exclusions: 'Do NOT call `query`, `suggestion`, or any NotebookLM-backed tool' and 'Base all verdicts exclusively on the code evidence returned by this tool.' This makes the when/when-not boundaries very clear.

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