cos_task_reclaim

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

Annotations already indicate idempotentHint=true and destructiveHint=false, covering the safety profile. The description adds the 'zombie' condition and target state, but does not disclose side effects (e.g., changes to owner or timestamps), required permissions, or the existence of a dry_run mode. This is adequate but not rich.

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 a single sentence, front-loaded with the key verb 'Reclaim' and resource 'zombie in_progress tasks'. It is concise and to the point, though the term 'icebox+ready' is slightly cryptic.

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 three undocumented parameters and an output schema, this tool requires more contextual explanation. The description does not clarify what each parameter does, what 'icebox+ready' means in practice, or the default behavior when parameters are omitted. It is incomplete for an agent to use safely.

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?

The input schema has three parameters (dry_run, idle_hours, agent_session) with no descriptions and 0% schema coverage. The description makes no mention of these parameters, leaving the agent completely in the dark about their meaning, defaults, or how they affect the reclaim operation.

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 (reclaim), the resource (zombie in_progress tasks), and the outcome (to icebox+ready). It includes a specific condition (idle + owner session inactive) that helps distinguish it from generic move or ready tools. However, the phrase 'icebox+ready' is somewhat ambiguous about whether tasks go to one state or both.

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 a use case (reclaiming zombie tasks) but provides no explicit guidance on when to use this tool instead of alternatives like cos_task_move, cos_task_ready, or cos_task_reconcile. There are no 'use when' or 'do not use when' instructions, leaving the agent to infer context.

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