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

Annotations already establish readOnly, non-destructive, and open-world behavior, so the disclosure bar is lower. The description usefully defines what constitutes an instance and clarifies that filtering is applied to activity/start times, but says nothing about the shape of the result (a single number?), whether the account scope comes from the session context, or cost across large windows. Note idempotentHint=false on a pure count is unintuitive, though the description does not contradict it.

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?

One front-loaded sentence that packs the counting unit definition first and the optional filters second, with no filler. The nested parentheticals make it dense to parse, but nothing is wasted.

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 three-optional-parameter count with full schema coverage and clear annotations, the description covers the counting unit, the two filter concepts, and the accepted time format. Remaining gaps—the return value and how the account is scoped—are small given there are no annotations gaps to compensate for.

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 real meaning: the accepted ISO 8601 date or date-time format for occurred_after/occurred_before, the origin of version_id via list_versions, and a slightly different framing of the version filter (activity in a version vs. a progression event) than the schema wording.

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 and resource ("Count progression instances for this account") and defines the counting unit with "each instance is one player starting one progression," which prevents the agent from confusing it with counting events or matches. It never explicitly names which sibling to prefer, so it stops just short of the top score.

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?

Guidance on the two optional filters is clear: restrict by game version and/or by a start-time window, and it cross-references list_versions for obtaining version_id. However, it never says when to use this counter instead of get_progression_report, count_over_time, or list_progression_types, so the agent must infer the boundary from the name alone.

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