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

With no annotations provided, the description carries the full burden and does so excellently. It discloses deterministic extraction, the types of claims checked, that a single sealed report is produced, per-claim details, and conservative behavior (no guessing, explicit claim counts). This far exceeds baseline expectations.

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 information-dense but not bloated. The list of example claim types is lengthy but valuable for calibrating expectations. It front-loads the core action and then explains behavior, making it easy to scan. Slightly over the two-sentence ideal but every clause earns its place.

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 absence of an output schema and the complexity of the auditing task, the description is remarkably complete. It explains the return format (per-claim quote, verdict, trail), the scope (explicit claim count, no full coverage), and the behavioral constraints, leaving the agent with a clear mental model.

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 schema already covers both parameters (text and seal) with clear descriptions, providing 100% coverage. The tool description adds minimal parameter-specific meaning beyond the schema (e.g., mentioning the sealed report aligns with the seal parameter), so the baseline of 3 is appropriate.

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 specifies the verb 'audit' and the resource 'a whole text,' while detailing exactly what the tool does: it identifies checkable quantitative claims, verifies them, and returns a sealed coverage report. It distinguishes itself from siblings like 'verify' and 'report' by emphasizing deterministic extraction and a consolidated coverage report.

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 implies when to use this tool: when auditing a full text for quantitative claims, with a conservative approach. It notes limitations ('never guesses and never implies full coverage') but does not explicitly name alternative tools or state when not to use it, which would earn a 5.

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