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

Goes well beyond the readOnly/destructive annotations: unguessable 128-bit token URL, ~15-minute expiry, re-run for a fresh link (consistent with idempotentHint=false), UTC timestamps, inclusion of system columns, the export rate class (12/hour per token), and an explicit data-privacy note. No contradiction with 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?

Front-loaded with the core action and return medium, and most sentences carry distinct behavioral facts (expiry, rate limit, privacy). It is on the longer side and reiterates some file-content detail that the output schema also covers, but little is pure 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?

For an export tool with a rich output schema, the description supplies everything the agent needs to call it correctly: format implications, link lifecycle, rate class, column naming, and privacy constraints are all covered.

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 100%, so the baseline is 3; the description earns extra by clarifying column-naming semantics (Q-codes as returned by get_survey, or custom IDs via useCustomID) and the extra system columns present in the file. It does not add format/behavior nuance for answersAsText or loopsIsOneRow beyond the schema.

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, resource, and scope: exports ALL responses of a survey as a downloadable file with columns/rows structure. It also names the sibling it is not (list_survey_responses) and the return medium (temporary link, never inline bytes), so the agent can place it precisely among siblings.

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?

Explicitly routes the agent: 'suited to large data sets; list_survey_responses returns the same data inline', naming the alternative and the condition that selects it. It adds further selection context (file usable for analysis outside built-in stat tools) so use-vs-alternative is unambiguous.

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