Store Screening Answers

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

Annotations flag destructiveHint and idempotentHint, and the description earns its keep beyond them: it explains exactly what replacement means for an existing question, that formatting (markdown bold, headings, bullets, backticks, dashes) is stripped before storage, that line breaks are kept, that content is not verified, and that an empty-after-stripping answer is a 400 that stores nothing. That is precise mutation and failure semantics, which annotations alone cannot convey.

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 purpose and the generate_qa_answers contrast are front-loaded in the first sentence, and the remaining detail is all behaviorally load-bearing. The dash and formatting enumeration is granular enough to border on over-specification, but every sentence carries information an agent could act on.

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?

There is no output schema, but the description supplies the return shape and field meanings ([{id, kind, prompt, answer, model_used, created_at}], with model_used naming the agent). Combined with the mutation, dedup, and error behavior, an agent has everything needed to call this correctly and interpret the result.

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 only 50%, and the description compensates well for the answers array: it defines per-question entry semantics, the replace-vs-add matching rule (same words, case and spacing ignored), and the stored-text normalization, none of which is in the schema. application_id remains undocumented in both places, which keeps it from a 5.

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 concrete verb and resource ('Store screening-question answers') and immediately contrasts with the sibling that generates them instead ('generate_qa_answers has the app's configured model write them'). An agent can distinguish this from generate_qa_answers, list_qa_entries, and record_filled_answers without opening a schema.

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?

It names the alternative (generate_qa_answers) and the condition that picks this tool: the caller supplies the text themselves. It also states the repeat-call behavior ('a repeated call changes nothing'), which tells the agent re-invocation is safe. It stops short of an explicit 'do not use when' statement, so a 4 rather than 5.

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