lab_collect

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

The description adds real context beyond the annotations: it names the evidence root as the write destination, flags the kernel dump as opt-in, and rules out starting a new test. But the annotations declare destructiveHint=true and idempotentHint=false, and the description never explains what may be overwritten or whether repeated collects on the same run_id clobber prior evidence — a notable omission for a destructive tool.

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?

Two tightly packed sentences with the action and destination front-loaded and the two key constraints (opt-in dump, no test started) following. Nothing is redundant or padded.

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?

An output schema exists, so return values need not be described, and the destination and opt-in behavior are covered. But for a destructive, non-idempotent mutation with four wholly undocumented parameters, the description leaves too much unsaid about the required identifiers and the overwrite semantics of the evidence root.

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 must carry the burden, yet it only touches include_kernel_dump indirectly via 'a kernel dump is opt-in'. The three required parameters (vm_name, package_id, run_id) receive no explanation of meaning, format, or where the package_id/run_id values originate.

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 ('Collect') on a specific set of resources (logs, events, diagnostics, dumps) and names the destination (HYPERV_MCP_EVIDENCE_ROOT). The clause 'no new test is started' implicitly distinguishes it from lab_verify/lab_stage, though it stops short of naming those siblings.

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 scope note 'a new run's logs' plus 'no new test is started' tells the agent the precondition (a run must already exist), and 'kernel dump is opt-in' clarifies the option. However, there is no explicit guidance on when to choose this over lab_diagnostics or lab_verify, so the agent must infer the boundary from sibling names alone.

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