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

With annotations declaring only non-readOnly/non-destructive, the description carries real load and delivers: server-side transition selection, exactly what a reopened task clears (assignee, plan with AI estimate, closing resolution) and what is preserved (approver, reviewer, tester), the bug-leaves-version behavior, and the refused-stage rule. This is well beyond what the annotations convey and is consistent with them (mutating, non-destructive).

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 purpose is front-loaded, and each subsequent sentence adds operative detail (transition rules, reopen semantics, return payload), so little is wasted. The middle section is a dense run-on string of clauses that is harder to parse than it needs to be, keeping it short of a 5.

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?

There is no output schema, so the description must explain returns and it does: the job for the task, available outcomes, where the task goes on done and on return, task context, and the once-per-session conventions/memory. Combined with the fully-covered input schema, an agent has enough to invoke and interpret it correctly.

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%, so the schema already documents ID, key, run and localRepositories, including their descriptions. The description only indirectly touches runKey ('once per session... unless the product context with the same runKey already delivered it'), which concerns return behavior rather than parameter meaning, so baseline 3 is appropriate.

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 opening sentence states a specific verb and resource ('Takes a task or bug into work or returns to it') and the mutations distinguished from siblings like task_done and task_publish. However, the meaning of 'take' relies on the following clause to become unambiguous, so it is clear but not instantly self-contained.

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?

It spells out the conditions under which the server applies each transition (draft published, deployment back to work, 'any' stage assigned to token owner) and that 'another employee's stage is refused', which tells the agent when this call applies vs. not. It does not explicitly name sibling alternatives (e.g., when to prefer task_done over take), leaving some routing to inference.

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