collect_docker_optimization_workload

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

The description adds materially to the annotations by disclosing that a failed attempt after workload-lease issuance is charged and halts further build/collection operations in the session, and that the call must not be retried unchanged. It also reassures that the caller cannot select images, commands, mounts, networks, Docker options, or host paths, which is meaningful beyond destructiveHint=true.

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?

Three sentences, each earning its place: purpose, caller constraints, and critical failure/retry behavior. The key action is front-loaded 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?

Despite an available output schema and annotations, the tool has 10 parameters with 0% schema coverage and no per-parameter explanation in the description. The high-level safety and session-blocking behavior is covered, but the agent cannot correctly choose values for mode, event_source, call_graph, or the time/output bounds without external knowledge.

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 0%, so the description carries the burden of explaining parameters. It only implies that inputs are 'bounded evidence' and vaguely maps session/Build to session_id/build_id; it does not explain mode, events, call_graph, event_source, frequency_hz, duration_seconds, max_output_bytes, or workload_timeout_seconds.

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 operation: run and collect bounded evidence from a verified image Build tied to a one-confirmation optimization session. It also explicitly scopes what the tool is not for ('never an image, command, mount, network, Docker option, or host path'), which differentiates it from sibling collection tools like collect_docker_target and collect_managed_docker_workload.

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 gives clear context: use only for a verified Build from a one-confirmation optimization session, and the caller chooses bounded evidence rather than arbitrary Docker inputs. It does not explicitly name alternative tools or state 'use X instead', but the constraints are strong enough to infer when this tool is appropriate.

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