Get Depot CI CPU and memory metrics

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

Annotations already mark it read-only and idempotent, and the description adds meaningful behavioral context: metrics for a running attempt change between calls, a snapshot time is reported, and the response includes the raw document because Depot publishes no field names. It also discloses the resource-exhausted failure mode and a workaround.

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 front-loaded with the core purpose, then flows from usage triggers to parameter behavior to response shape and failure handling. Every sentence adds information; no filler or repetition.

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, the description does not need to enumerate return fields, and it still covers param semantics, changing-data behavior, response composition, and error handling. An agent has enough context to select and invoke the tool correctly.

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, but the description adds important semantic detail: the level is inferred when omitted, and the server tries run, then job, then attempt. This goes beyond the schema's parameter descriptions and clarifies how 'level' and 'id' interact.

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 opens with a specific verb and resource: 'Read CPU and memory metrics for a Depot CI run, job, or job attempt.' The stated use cases (OOM kills, exit 137, under-provisioned runner) set it apart from sibling tools like depot_get_ci_logs and depot_get_ci_job_summary.

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?

It explicitly instructs when to use the tool: when a job died without a useful error, was killed, hit exit 137, or is slow. It gives diagnostic patterns (memory at limit, CPU pinned) but does not name specific sibling alternatives or say when not to use it.

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