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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered; the description adds substantial behaviour beyond that — per-field-type output shape (distributions for select/boolean/rating, min/max/sum/mean/median/stddev for number/rating) and the free-text truncation limit of five excerpts. These are exactly the traits an agent needs to set expectations about the response.

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?

It is longer than most definitions but front-loads the core claim and makes each sentence work: question examples, per-field-type behaviour, sibling routing, then an invocation example. Slight redundancy between the question list and the field-type explanation keeps it from a 5.

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?

An output schema exists, so return values need not be spelled out, yet the description still characterises the aggregate fields and the truncation behaviour. Combined with the invocation example, an agent has everything needed to call this correctly.

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 33% — only form_id carries a schema description, while since/until are undocumented. The description partly compensates by showing an example call with a since window and by motivating time-boxed queries ('how many came in per day'), but it never explains until, whether bounds are inclusive, or timezone handling. Partial compensation warrants a 3 rather than a 4.

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 gives a specific verb and resource ('Counts, distributions and averages for every field on a form, computed in one call') and immediately contrasts with the sibling that does something similar, list_responses. An agent can distinguish this summarisation tool from list_responses and export_responses without opening the 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 states the selection rule explicitly ('the right tool for almost any question about results') and enumerates concrete question shapes it answers, then names the exclusion condition: free-text fields return only excerpts, so 'call list_responses when the full text is what the person wants.' When-to-use and when-to-use-something-else are both present.

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