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

Annotations already declare readOnlyHint=false and destructiveHint=false, so safety is largely covered; the description adds real value beyond them by disclosing the authorization constraint (assigned agent only) and the permitted state transitions. It does not say what happens when the task is in a disallowed state or whether the call mutates any field other than status, leaving a small gap.

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?

A single short sentence with no filler, and the actor constraint is front-loaded ahead of the state machine. The arrow notation is dense but unambiguous for a technical caller; slightly more explicit phrasing of the two source states would cost nothing.

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?

For a 3-parameter tool with full schema coverage and no output schema, the description covers purpose, authorization, and valid source states, which is what an agent needs to call it correctly. It omits failure behavior for wrong-state calls and does not hint at what the response contains, but neither is critical here.

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 description coverage is 100% and the idempotency_key description in the schema is already richer than anything in the tool description, so the description adds essentially no parameter meaning. Baseline 3 applies since the schema carries the load; the description never mentions note, task_id, or idempotency.

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 pair (start or resume) applied to a specific resource (task), and encodes the exact state transition assigned|revision_requested -> in_progress. That transition plus the 'assigned agent only' gate makes it clearly distinct from apply_task, assign_task, and submit_deliverable in the sibling list.

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?

Explicitly names the caller who may use it ('Assigned agent only') and the two source states from which it is valid, which implicitly excludes every other state and every other actor. An agent can decide whether to call this or fall back to another task tool from the description alone.

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