check_defined_terms

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

With no annotations, the description carries full burden. It discloses the heuristic nature with a BETA warning, explains the output categories, warns that 'used_never_defined' is a heuristic candidate list, notes the scope ('Body-level paragraphs only'), and states 'Read-only.' This exceeds the typical transparency level.

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 dense but each sentence adds value: warning, purpose, pattern examples, output categories, scope, and read-only flag. It is front-loaded with the BETA warning. Slightly long, but structured and free of 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?

Covers the heuristic risk, the exact outputs, and the scope limitation. An output schema exists, so detailed return format is not required. Minimal omissions (e.g., whether it works on non-legal documents) are minor given the specificity already present.

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 0%, so the description must compensate. It explains 'definition_patterns' in detail (regexes capturing group 1, defaults overridable). It does not explain 'file_path', but that parameter is self-evident from its name and common across tools. The meaning added is meaningful and reduces ambiguity.

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?

States a specific verb ('Audit') and a well-defined resource ('a legal document's defined terms'). It lists the specific categories it reports, making it unmistakably distinct from sibling audit tools like validate_document or diagnose_document. No tautology.

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 usage when auditing defined terms, but does not explicitly contrast with alternatives or state when not to use it. It names no sibling tools or conditions for alternative selection, leaving the agent to infer that this is the right tool for defined-term audits.

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