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

Annotations already declare readOnly/non-destructive, but the description adds real behavioral context beyond them: the required submissions:read scope, Japan-time month semantics with inclusive ends, free-text exclusion, and an explicit privacy guarantee that nothing respondent-identifying is returned.

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 what you get back, followed by parameter and privacy notes; every clause carries information. Dense but no filler, though the parenthetical formula and nested parentheticals make it slightly hard to parse at a glance.

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?

With no output schema, the description fully carries the return-shape burden (per-field {value, label, n}, average, score) and covers scope, time semantics, exclusions, and privacy. An agent has everything needed to call it and interpret results.

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, but the description adds meaning the schema lacks: the Japan-time zone of from/to, that both ends are inclusive, and that omitting them returns all time. It also clarifies the NPS score computation.

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?

Specific verb (read) and precise resource (a form's aggregated stats), plus exactly what is returned: per-choice/rating/NPS {value, label, n}, a rating average, and an NPS score with its formula. This is unambiguously distinct from siblings like list_submissions or get_submission.

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 gives clear operational context: requires the submissions:read scope, from/to are optional months and omitting them means all time, and free-text answers are excluded. It stops short of naming a sibling alternative explicitly (e.g. 'use list_submissions for raw answers'), so no full 5.

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