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

Annotations already declare destructiveHint=true, and the description adds valuable context with 'remove' and 'so they never execute', implying irreversibility. It also describes the per-item results structure ({queue_ref, success, error?}) and the workflow prerequisite, which goes beyond the structured annotations without contradicting them.

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 organized into sections (WHEN TO USE, WHEN NOT TO USE, RETURNS, WORKFLOW) making it scannable. However, the Chinese trigger sentence is extraneous and redundant, and the WHEN NOT TO USE section contains generic statements that do not specifically apply to this tool, adding noise without earning their place.

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?

With no output schema, the description provides a concise return format, which is sufficient. It includes workflow guidance and distinguishes the batch nature. Minor gaps include not explicitly mentioning the relationship to activate_run_queue_items or the singular variant, but the overall context is adequate for selection and invocation.

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%, with both parameters well-documented: queue_refs includes example formatting and an explicit note to obtain values from list_run_queue_items; reason is described as optional. The description does not add new parameter semantics but reinforces the workflow, so it meets the baseline without going above.

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 tool's function: 'Release (remove) one or more CoreClaw Run Queue items so they never execute.' This specifies the verb, resource, and effect. It also distinguishes itself from the singular sibling by explicitly calling itself 'the batch version.'

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 WHEN TO USE section provides clear context ('when the user no longer needs queued runs and wants to remove them in bulk') and the WORKFLOW indicates a prerequisite (call after list_run_queue_items). However, the Chinese trigger is overly broad and mismatched, covering query/run/rerun/stop/export/view rather than removal, which could mislead an agent. The WHEN NOT TO USE section is generic and does not address alternatives like the singular release_run_queue_item or activate_run_queue_items.

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