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

Annotations already declare readOnly/idempotent/non-destructive, yet the description adds real behavioral context the annotations cannot: pending approvals are surfaced, the tool is meaningful even before a run starts, 'accepted/queued is not completed', and approval decisions cannot be made here (the owner must act in Fine Structure). That last point prevents an agent from attempting an action this tool cannot perform.

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?

Purpose is front-loaded and every sentence carries distinct state semantics. The pair 'Task scheduling state is separate from run outcome' and 'accepted/queued is not completed' overlap somewhat in intent, which keeps it from a perfect score.

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 must convey what comes back, and it does name the payload (latest execution status, pending approvals). It stops short of describing error behavior (e.g. unknown task_id) or any polling/refresh expectation, which for a status-polling tool would be the remaining useful detail.

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 50%: agent_id is documented in the schema ('Owned agent ID from list_agents') while task_id is not. The description partially compensates by explaining where a task_id originates (returned by send_agent_message or list_agent_tasks), but adds no format or validity detail. This matches the baseline for a schema doing roughly half the work.

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 (check) and resource (a durable task), and anchors it to its producers: 'returned by send_agent_message or list_agent_tasks'. An agent can distinguish it from list_agent_tasks (enumeration) and get_agent_conversation (the answer text) without reading any schema.

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?

'Read the conversation for the actual answer' implicitly routes the agent to the sibling that holds the result, and the note that scheduling state is not run outcome tells the agent how to interpret what it gets back. It never states an explicit when-not-to-use or prerequisite, so it falls short of full alternative guidance.

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