get_form_submissions

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

The description adds meaningful behavioral information beyond the annotations. While annotations already mark readOnlyHint and destructiveHint false, the description explicitly reassures 'Reads only; submissions are not deleted, and nobody is subscribed or emailed.' It also warns about PERSONAL DATA handling, requires an API key, and clarifies that an empty result is not an error. These details are not present in the annotations and significantly enhance the agent's understanding of side effects and prerequisites.

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 well-structured and mostly concise. It front-loads the core purpose, then adds usage guidance and safety notes. Some redundancy exists, e.g., 'Reads only; submissions are not deleted, and nobody is subscribed or emailed' repeats information already implied by the readOnlyHint and destructiveHint annotations map to 0 indices from structured data (though the phrasing adds clarity). The mention of 'Requires an API key' is extra but arguably outside the tool's direct scope believe it's useful). Overall, it is tight and purposeful, earning a 4 rather than a 5 due to slight 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 tool complexity (list with pagination) and rich schema, the description covers the essential aspects: what it does, what data it returns (values in each field), read-only safety, API key requirement, and the normal empty-result case. It doesn't specify the exact return structure (e.g., array format), but without an output schema, this is a minor gap. The description is sufficient for an agent to decide and use the tool correctly, so a 4 is justified.

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 input schema already provides descriptions for all three parameters (form_id, page, limit) with high coverage (100%). The description adds no extra meaning to these parameters—it doesn't elaborate on pagination behavior, default values, or parameter formats. It does mention the form context via 'a signup form' and notes personal data is returned, but this is not parameter-specific. Given the schema fully covers parameter semantics, a score of 3 is appropriate.

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 opens with a specific, action-oriented statement: 'List the submissions a signup form has received, including the values entered in each field.' This clearly defines the tool's primary function and scope (submissions per form), distinguishing it from related tools like get_form. It also specifies the type of data returned (values entered in each field), leaving no ambiguity about the tool's purpose.

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 tells when to use the tool ('Use it to see who signed up and what they told you') and provides a direct alternative for a related use case: 'For the form's own definition, use get_form.' It also clarifies important usage nuances, such as 'Reads only; submissions are not deleted, and nobody is subscribed or emailed' and 'No submissions is a normal answer, not an error,' which help the agent decide when to invoke this tool.

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