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

Annotations already declare readOnlyHint/openWorldHint/destructiveHint, yet the description adds substantial behavior beyond them: the Pro-feature gate and its UPGRADE_REQUIRED terminal behavior (including history recorded while Pro), the deduplication semantics that make breakdown counts unique visitors while totalEvents is the raw pre-dedup count, and the specific response shape when from/to are omitted (period: { from: null, to: null }).

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 most important facts are front-loaded: what it returns, then read-only, then prerequisites. It is dense but each sentence carries distinct information (return shape, dedup rule, default period, gating). The only minor waste is 'Read-only', which the readOnlyHint annotation already conveys.

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 a 7-parameter read tool with no output schema, the description compensates fully: it documents the return object keys, the meaning of totalEvents vs deduplicated breakdown counts, the all-time default period, and the error path for non-Pro workspaces. An agent has everything needed to call and interpret it.

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 baseline is 3, but the description goes further by stating that rate metrics are 0–100 numbers vs integer counts, that breakdown counts are per-unique-visitor, that includeEvents returns sanitized events without visitor IDs, and by restating the from<=to constraint. That adds real interpretive value over the property descriptions.

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 verb+resource ('Get form analytics') and enumerates exactly what is returned: views, submissions, completion rate, bounce rate, and device/browser/country/traffic-source breakdowns. This clearly distinguishes it from siblings like form_list, form_get, and formSubmission_list, which serve different purposes.

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 an explicit prerequisite ('Use form_list to find formId first') and a concrete usage recipe ('for completion on one device, filter by device and read completionRate'), plus the Pro-plan condition that yields UPGRADE_REQUIRED. It stops short of stating when *not* to use it, but no competing analytics sibling exists, so the routing guidance is largely complete.

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