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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so safety needs no restating. The description adds genuinely non-obvious behavior beyond that: strict ownership scoping ('Only your own tasks') and the resulting not_found outcome for anything else, plus the fact that a failed task carries error_message rather than raising.

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?

One sentence, front-loaded with the resource and its state space, followed by the scoping caveat. No filler and nothing an agent must read twice.

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?

An output schema exists, so return structure needn't be documented, and the description still usefully sketches the state machine and error field. For a single-parameter getter this is nearly everything an agent needs; only polling behavior on an in-flight task is left 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?

Schema description coverage is 0%, so the schema only tells the agent that task_id is a required string up to 64 chars. The description compensates partially by implying the id originates from the start call that launched the task and that ownership is checked, but it gives no format or provenance detail beyond that.

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 ('Status of a background task') and immediately scopes it to tasks 'you started', naming the producer sibling synthesize_agent. The enumerated outcomes (queued, running, succeeded, failed) tell an agent exactly what this returns, distinguishing it from every other get_* sibling.

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?

The parenthetical '(e.g. synthesize_agent)' links this tool to the async operation that precedes it, which is the key usage cue. It does not explicitly say how often to poll or what to do if the task is still running, but the retrieval context is clear and no competing alternative exists among the siblings.

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