task_device_tasks__list_task_runs

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description adds genuinely non-obvious behavior: runs are listed collectively rather than as children of the parent task, and run data 'might easily survive their parent task', which tells the agent results may outlive the referenced task and that runs must be correlated manually.

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 first sentence front-loads the verb, resource and endpoint clearly. The trailing 'Info' block with AIP-152 citation and ESET vocabulary note is mildly padded but does convey the modeling convention, so waste is limited.

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 six-parameter paginated list tool with no output schema, the description covers scope and the forensics/collective-listing semantics but says nothing about what a task run record contains or result ordering. Pagination is handled by the schema, so nothing critical is missing, but the picture is only adequate.

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 100%, so all six parameters (taskUuid, deviceUuid, pageSize, pageToken, fields, listOnlyLastRuns) are already documented in the schema. The description only reinforces that the list is scoped to a single task and adds nothing about filtering by device or the last-runs-only option, so baseline 3 applies.

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 uses a specific verb and resource ('List task runs', 'all the runs of the task') and names the endpoint, so an agent knows it retrieves run history scoped to a single task. It does not explicitly distinguish itself from siblings such as task_device_tasks__list_tasks or __get_task, relying on the 'runs' vocabulary to do that implicitly.

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 mention of 'For the sake of forensics' implies an investigative use case, and the required taskUuid implies scope, but there is no explicit statement of when to use this versus list_tasks or get_task, and no prerequisites or exclusions are given.

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