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

Annotations already declare readOnlyHint=true and destructiveHint=false, but the description adds explicit clarity by stating 'Nothing is written' — reinforcing the read-only nature and that no data is mutated. It also mentions the input format (PDF, DOCX, XLSX, CSV) and size limit (max 20 MB), which are not in the schema. This adds valuable behavioral context beyond annotations.

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 (two sentences) with no fluff. It front-loads the verb and purpose, specifies the input constraints, and ends with a clear next-step pointer. Every word adds value, making it appropriately sized and efficient.

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 tool's moderate complexity (3 parameters, no output schema, no nested objects), the description fully covers what an agent needs: input formats, size limit, scope of action (no writes), and the follow-up step (add_question). The lack of an output schema is not an issue because the description clearly states the output is a 'review-ready list of questions,' which is sufficiently descriptive for anticipated use.

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 description coverage is 100%, so the schema already documents each parameter (url, filename, survey_id). The description adds context about the URL being 'public http(s)' and survey_id referencing list_surveys, but these are minor additions. The baseline of 3 applies since the schema handles parameter semantics adequately.

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: 'AI-parse a questionnaire document... into a review-ready list of questions with types, answers and skips.' It specifies the resource (questionnaire document), the action (parse), and the output (list of questions). This distinguishes it from sibling tools like add_question and list_questions, which operate on already parsed questions.

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 when to use this tool ('feed the result into add_question') and what it does not do ('Nothing is written'), which implies it is a read-only preparation step. It also implicitly differentiates from sibling tools like upload_media (which is for media) and suggests the workflow: parse first, then add.

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