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

Annotations already declare idempotentHint=true and destructiveHint=false, so the safety profile is covered; the description goes further by disclosing the return payload (task plus notes_taken) and the lifecycle side effect that waiting notes are consumed at task completion. What is missing is any statement about preconditions or failure modes, such as what happens if the task was not handed to an agent.

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 action and its effect are front-loaded, which is good, but the middle clause is a run-on with nested parentheses and semicolons ('newer than get_agent_work may have shown; they count as handled once you finish the task') that forces a re-read. The informational content is worth keeping; the packaging is not.

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 usefully summarizes what comes back and what the agent should do with it ('follow them'), which an agent needs to act correctly. For a one-parameter mutation tool this is close to complete, though error behavior and the exact required task state remain unstated.

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?

There is one required parameter with 0% schema description coverage, so the description must carry the meaning. 'A task handed to an agent' does narrow task_id to agent-assigned tasks, but it never states the format, whether the task must be in a particular state, or what an invalid id produces.

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 and resource ('Mark a task ... as being worked on now') plus the visible effect ('its line runs in the user's day'), which is more than a restatement of the name. It implicitly contrasts with finish_task_work and get_agent_work but never names finish_task_work as the closing counterpart, so sibling differentiation is only partial.

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?

'Call it before working on the task' gives a clear timing rule, and the note that the returned notes 'count as handled once you finish the task' implies the hand-off to finish_task_work. There is no explicit when-not guidance (e.g. what to do if the task is not assigned to this agent) and the complement tool is not named.

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