find_unsupported_words

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

With no annotations, the description takes full responsibility for behavioral disclosure. It explains how numbers and words are checked (arithmetic vs embedding similarity), normalisation, and that it returns evidence for human judgment. It also clarifies there is no threshold, adding depth.

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 succinct and logically structured: purpose, method, and clarification. Every sentence contributes value, with no redundancy.

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 output schema exists, return format is not needed. For a tool with 4 params and 2 required, the description provides enough behavioral context for an agent to invoke it appropriately. Minor gap: no mention of side effects or rate limits, but for an analysis tool this may not be critical.

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 0%, so the description must compensate. It explains 'answer' and 'sources' but does not explain 'k' or 'locale'. The mention of 'floor' hints at k but is ambiguous. Only partial coverage for half the parameters.

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 states exactly what the tool does: identifies the words an answer's sources least support, paired with closest matches. It clearly distinguishes from a verdict tool, making its purpose unambiguous.

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 explicitly states what it does not do (i.e., does not return a verdict) and directs the user to interpret evidence themselves. This provides clear context, though it doesn't name alternatives (none exist).

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