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

The description adds meaningful behavioral context beyond the annotations: it explains the effect of priority on ordering ('due postponed cases are handled first, then higher priority'), guarantees that runs are not interrupted and status is unchanged, and clarifies that setting `none` resets to default. This is valuable since the annotations only provide basic readOnlyHint, idempotentHint, and destructiveHint flags. No contradictions with annotations.

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 exceptionally concise: three sentences, each earning its place. The first states the core purpose, the second explains behavioral implications, and the third clarifies a special parameter value. It is front-loaded with the most critical information and contains zero fluff or repetition.

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?

The description provides the core operation and key behavioral traits but leaves out some important context for a 6-parameter tool with nested objects. It doesn't explain the selection mechanism (case_ids vs all_matching with filters/search), the role of queue_id (why it's required), batch size limits, or error handling. While the schema covers these details, the tool description could benefit from a brief overview linking the parameters together.

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 input schema already adequately describes each parameter, including the priority enum and case_ids limits. The description adds minimal parameter-specific insight beyond reinforcing that `none` clears priority (already in the schema). The description does provide broader behavioral context (like how priority affects ordering), but that's not parameter-specific. Baseline 3 is appropriate.

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 starts with 'Set the priority of multiple cases,' providing a specific verb and resource. It clearly explains that priority affects only the order of pending cases and explicitly states what the tool does not do (interrupt runs, change status), which distinguishes it from sibling tools like bulkUpdateCaseStatus or bulkReprocessCases. The mention of 'Set `none` to clear priority back to the default' adds further precision.

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 implies when to use this tool (when you need to change priority for multiple cases) and explicitly says what it doesn't affect (runs, status), which helps avoid misuse. However, it does not provide explicit guidance on when not to use it (e.g., for single cases, use updateCase instead) or name alternative tools. The advice is implied rather than explicit.

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