Create a durable task

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

Beyond the annotations, the description discloses that the task is initially pending, durability depends on the sqlite tasks backend being enabled, ttl_ms is only an expiry hint, and auth requires a tool policy gate plus plan quota. This is meaningful behavioral context beyond readOnly/idempotent flags.

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 description is compact and front-loaded: the core purpose appears first, followed by usage guidance, exclusions, behavioral traits, and auth. Every sentence earns its place and there is no filler.

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 an output schema present and full parameter descriptions, the tool description covers the essential operational context: what it creates, durability caveats, how to interact with the result, what not to use it for, and auth requirements. No critical gaps remain.

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?

The schema already documents all three parameters at 100% coverage, so the baseline is 3. The description adds value by clarifying that ttl_ms is a handle expiry hint rather than a strict guarantee, which is not fully captured by the schema's 'suggested time-to-live' phrasing.

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 description states a specific action and resource: 'Create a durable async task handle (pending)'. It also distinguishes the tool from siblings by explicitly saying it starts long-running work polled with tasks_get or tasks_list, and by excluding memory_write and plan_cache_put.

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?

Usage guidance is explicit: use it for long-running work you will poll with tasks_get or list with tasks_list, and do not use it for storing facts or plans. The auth note adds another practical precondition, making the selection criteria very clear.

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