task_fail

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

Annotations declare destructiveHint=false and openWorldHint=false, which is somewhat consistent since marking a task as failed is not destructive in a data sense but is a state change. The description adds that it 'unblocks other agents' and that the body is recorded on the comment log, which is useful behavioral context beyond annotations. It does not contradict annotations, so a 4 is appropriate.

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 well-structured, starting with a deprecation notice, then the core action, then usage guidance. It is slightly verbose with the deprecation notice taking prime space, but it's important for routing agents to alternatives. The content is concise and front-loaded with the most critical info.

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 is complete for the tool's purpose, including deprecation status, usage guidance, and why to use it over alternatives. The output schema exists but the description doesn't explain return values, but that's not necessary since output schema exists. It covers prerequisites (claimed task) and the effect on other agents. Slight gap: no mention of prerequisites like being a claimer, but that's implied.

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 description explicitly explains both parameters: task_id is 'ID of a task you have claimed' and body is 'Optional reason recorded on the task's comment log. Strongly recommended.' This adds value beyond the schema, which only gives terse descriptions. The description also provides rationale for using body, which is helpful.

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 purpose: 'Mark your claimed task as failed.' The verb 'mark' and resource 'task' are specific, and the description distinguishes it from task_unclaim by stating when to use each. It also mentions that the harness now owns this functionality, adding context. However, it doesn't explicitly contrast with all sibling task tools like task_complete, so it loses a point.

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 explicit guidance on when to use: 'Use when you cannot complete it.' It also explicitly contrasts with task_unclaim: 'If you're stepping away but the task isn't truly failed, use task_unclaim() instead.' This is a clear when-to-use and when-not-to-use, naming the alternative tool.

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