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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=true, so the safety profile is covered and the bar is lower. The description adds genuinely non-obvious behavior: the zero-filter default counts every match on record, and time bounds are inclusive-or-not via occurred_after/before with ISO 8601 accepted formats. It does not say whether the count is exact or eventually consistent, nor what account scoping implies for permissions.

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?

Three tight sentences, front-loaded with the verb and resource, then filters, then the alternative. The only redundancy is "With no filters, counts every match on record," which largely restates the optionality of the preceding sentence, though it does pin down the default.

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 read-only count with no output schema, the description covers scope, filter sources, format, and the unfiltered default — enough to call it correctly. The remaining gap is the return shape (an integer count) and any guarantee of exactness, which is minor for a counting tool.

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 all three parameters are already documented, giving a baseline of 3. The description adds real value by naming list_versions as the lookup for version_id and by specifying ISO 8601 date-or-date-time for the time bounds, but it does not clarify the boundary semantics (inclusive vs exclusive) or how the two time filters combine with version_id.

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 matches") plus the scope ("for this account"), which cleanly separates it from count_events, count_players, and count_progression_instances by resource. It also distinguishes itself from the reporting family (create_report/run_report) by framing itself as the plain-count option.

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?

Gives explicit routing guidance: "Prefer this over a report for plain match counts," and points to list_versions as the source of version_id values. It covers the default case (no filters = all matches) but never states when *not* to use it, e.g. when per-match detail is needed (get_match/list_recent_matches).

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