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

Adds real behavioral context beyond annotations: it returns the task to To do, admins have broader scope, and a foreign hold refuses with TASK_TAKEN. This explains the outcome and a notable failure mode the annotations don't cover.

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?

Two tightly packed sentences — the state transition is front-loaded, followed by permission scope and failure behavior. No wasted words.

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 annotations, full schema coverage, and an output schema, the description covers the core action, permission scope, and a key error. Adequate to invoke correctly; only missing explicit sibling routing.

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%, including a documented `why` field, so the schema carries parameter meaning. The description adds nothing parameter-specific, so baseline 3 applies.

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 (stop) and resource (task) plus the exact state transition: back to To do. Clear what it does and that it applies to tasks you hold, though it doesn't explicitly name task_cancel/task_complete as alternates.

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?

Implies the condition (a task you hold, admin can stop anyone's) but gives no explicit when-to-use-vs-alternatives guidance against siblings like task_cancel, task_complete, or task_reopen.

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