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

Goes well beyond the annotations: it discloses the lease model and default duration, the renewal rule (renewing never shortens an existing hold), the exact failure mode with error code and payload field, and the shape of the return (task with holder, content via task_get). That is real behavioral context an agent cannot get from readOnly/destructive/idempotent hints alone.

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?

Four dense sentences, zero filler, front-loaded with the core verb-and-effect statement before edge cases and error behavior. The pointer to task_get sits at the end where it belongs.

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 lease-based mutation tool with full schema coverage and an output schema, nothing an agent needs is missing: success conditions, refusal condition, renewal semantics, and where the content lives are all covered.

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 100%, so the baseline is 3; the description earns one more by explaining what leaseHours actually does behaviorally (renewal never shortens the hold), which is not derivable from the numeric bounds in the schema. The 'why' parameter is left entirely to the schema, which is acceptable at full coverage.

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?

Names a specific verb (start) and resource (task), then defines the operation precisely: a free or lapsed-lease task becomes yours under a lease. It also distinguishes itself from task_get by explicitly deferring content retrieval to that sibling, so an agent can tell the two apart without opening schemas.

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?

States the conditions under which starting succeeds (free To-do, or an agent hold whose lease lapsed) and the one case it refuses (someone else's live hold, TASK_TAKEN with details.holder). It does not name the counterpart tools for releasing or finishing work (task_stop, task_complete), so the alternative-path guidance is implicit rather than explicit.

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