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

Discloses the key side effect — 'any queues not in the list will be unlinked' — well beyond the annotations' readOnly/destructive hints. Also adds the permission requirement and the success criterion (linked_queue_count > 0), which function as a post-condition. This is consistent with idempotentHint=true, since submitting the same full list twice yields the same state; no contradiction 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?

Three sentences with zero waste: the purpose, the replacement semantics, and the permission/verification steps. The critical 'full list' instruction is front-loaded immediately after the purpose statement, so an agent grasps the operational contract quickly.

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 moderate-complexity mutation tool with no output schema, the description covers purpose, side effects, permissions, and a verification path via getRevisionCaseQueueSetup, which effectively substitutes for return-value documentation. The remaining gap is that the direct response shape and edge-case behavior (e.g., an empty queue_ids array) are not addressed, though the confirm-call instruction mitigates this.

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 selected_automation_revision_id parameter already has extensive draft/active/historic semantics in the schema, and queue_ids already documents 'Full set of queue IDs... Replaces any existing links.' The description reinforces queue_ids' full-set meaning and ties build_id/integration_id to the 'case-queue integration slot', but adds little net-new meaning beyond the schema.

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 ('Replace') and a precise resource ('the set of queues linked to this build's case-queue integration slot'). The second sentence's 'full desired queue list' semantic makes the replace-all behavior unmistakable and separates it from additive siblings like attachRevisionIntegrations.

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?

Provides a clear invocation pattern ('Send the full desired queue list — any queues not in the list will be unlinked'), a precondition ('Requires edit permission on the agent'), and a named follow-up call (getRevisionCaseQueueSetup). It does not explicitly contrast with additive alternatives such as attachRevisionIntegrations or listRevisionIntegrationQueues, so when-not-to-use is left partly to inference.

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