test_step

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

Annotations already declare this a non-destructive, idempotent mutation. The description adds meaningful behavioral context beyond them: it affects the HUD strip label and is constrained to running runs. It omits error behavior outside a running session, but the state constraint is the key operational disclosure.

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 short sentences with zero filler; the core purpose and the running-run constraint are both front-loaded. Every clause carries information.

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, full parameter coverage, and annotations covering the mutation profile, the description supplies the remaining operational context: what is being set and the running-run restriction. The only minor gap is not stating what happens if invoked outside a running session.

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%, with both parameters documented and examples given in the schema itself. The description adds no additional parameter semantics, so the baseline of 3 is appropriate.

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 and resource: 'Set the running session's current step', with a concrete internal reference ('HUD strip's `iso_test step`'). The scope qualifier 'Running runs only' disambiguates it from start/finish/clear siblings, though it does not explicitly contrast with update_step/next_step.

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?

'Running runs only' implies the tool is only callable after test_start and during an active run, which is useful context. However, no alternatives or explicit when-not conditions are named, so the agent must infer the prerequisite and the boundary against test_finish/test_clear.

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