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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint. The description adds valuable behavioral context beyond that: results are keyed by Queue ID, zero counts are included, and foreign team Queue IDs are silently dropped. It also explains the team/API key scoping for team_id. This is useful, though not exhaustive (e.g., no pagination details), but the annotations cover the safety profile well.

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 description is four sentences, all dense with actionable information. It front-loads the purpose, then gives usage timing, key behaviors, and the alternative. While slightly long, every sentence earns its place, so it is concise without being terse.

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 tool with 4 parameters, no output schema, and moderate complexity, the description covers the purpose, when to use, alternatives, and important behavioral details (zero counts, silent drop, team scoping). It doesn't mention pagination or exact return format, but for an aggregation stats call, this is adequate. It could be more complete, but it is sufficient for an agent to invoke 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 description coverage is 100%, so the baseline is 3. The description adds semantics beyond the schema by explaining the meaning of the counts (waiting, review, pending, failed) and the behavior of foreign queue IDs being dropped, which directly informs the queue_ids parameter usage. It also clarifies the '1 to 100' limit per the schema. This adds meaningful context.

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 clearly states the action as 'Get case status counts for many Queues in ONE call', specifying the verb, resource, and scope. It distinguishes itself from listCases and searchCases by explicitly naming that it aggregates across multiple queues in a single call, making the purpose unambiguous.

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?

The description gives explicit usage guidance: 'Use this after listQueues whenever you need per-Queue counts' and contrasts with the alternative 'listCases with count_only=true' for a single queue with richer filters. This clearly states when to use the tool and when to use the alternative, leaving no ambiguity.

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