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

Beyond the destructiveHint annotation, the description reveals auth requirements ('Requires an agent bearer key'), lease time bounds (60–3600s, default 900), versioning expectations ('All require task expected_version'), and reviewer/reserve-editor timeout behavior. This is substantial added context. It doesn't elaborate on the actual destructive side effects or return behavior, but the annotation already flags destructiveness.

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 remarkably compact, front-loading the id meaning and then packing distinct constraints into short clauses. Every sentence adds new information: lease bounds, role restrictions, timeout review, policy source, versioning, and auth. There is no redundant prose or 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?

For a complex mutating tool with a nested object and no output schema, the description covers many operational constraints but omits what the tool returns (e.g., new version needed for the next transition) and the full legality of each action (e.g., when cancel or reopen are valid). These omissions matter because the agent must chain transitions safely. The description is useful but not complete enough for all edge cases.

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 id, lease_seconds, expected_version, and result reasonably well; the description adds task-specific meaning for id ('task entry ID') and maps several actions to authorized roles. However, the description omits any explanation for the 'reopen' and 'cancel' actions, and with 50% schema coverage and no action parameter description, that gap leaves the agent guessing about those transitions. It partially compensates but doesn't fully clarify every parameter or enum value.

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 names the resource ('task entry') and lists the state-changing actions (claim, renew, release, block, submit, complete), making it clear this tool transitions a space task's lifecycle state. It doesn't explicitly state 'transitions a task' as a purpose, but the action inventory and constraints leave little ambiguity. The action set distinguishes it from nearby siblings like report_task_progress or get_space_policy.

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 description offers strong role-based usage guidance: 'release/block/submit by live assignee', 'complete by the configured/eligible reviewer other than assignee', and 'a reserve editor may review after timeout'. It also points to get_space_policy for claim/progress/attempt limits, which tells an agent where to look for preconditions. It doesn't explicitly name 'when not to use' or alternative sibling tools, so it falls short of a 5.

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