test_finish

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

Annotations already declare non-readOnly, idempotent, non-destructive; the description goes beyond them by disclosing the real side effects — releasing the host lease and writing an evidence row on the linked project, with the qualifier "when there is one." It stops short of saying what happens to the lease on a failed call or error behavior.

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?

One sentence, front-loaded with the verb and outcome, with the side effects in a trailing clause. No filler; the only slight cost is the unexpanded HUD shorthand, which assumes familiarity.

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 annotations covering safety and an output schema covering return values, the description's main remaining burden is side effects and scope, which it largely fulfills (lease release, evidence row, project linkage). The gap is the undocumented `run_id` parameter and no note about idempotency semantics beyond the annotation.

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 only 33% — only `note` is documented. The description's "pass/fail" hints at the `result` enum but adds nothing about `run_id` (scope/format) or the consequence of each result value, so it does not compensate for the coverage gap.

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?

States a specific verb (finish a running session) plus outcome (pass/fail) and the concrete side effects (host lease release, evidence row). Clear and distinguishable from test_start/test_step/test_status, though it never names sibling test_clear or job_finish, which could plausibly be confused with it.

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?

"Finish a running session" implies it follows test_start, and the HUD equivalence gives context, but there is no explicit statement of when to use this versus test_clear or job_finish, nor any precondition (must the session be running?). Usage is implied rather than specified.

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