test_clear

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

Annotations already cover safety (readOnly=false, idempotent=true, destructive=false), and the description adds real context beyond them: the session transitions to state=idle and a held host lease is released, with 'still-held' signaling the release is conditional. It does not say what happens if no lease is held or whether the run record survives.

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?

A single front-loaded sentence with the effect (idle, lease release) stated up front and the CLI equivalent in parentheses. No filler; slightly telegraphic syntax ('state=idle, releasing...') but nothing wasted.

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 and annotations cover the safety profile, so the description needn't explain returns. However, for a required run_id with zero schema coverage, the definition leaves a genuine gap about what that identifier refers to and what failure modes exist.

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?

The single parameter run_id has 0% schema description coverage, so the description must carry its meaning. The description only refers obliquely to 'a session' and never mentions run_id, its format, or whether it identifies the session being dismissed — leaving the one required input essentially undocumented.

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 object ('Dismiss a session') plus the resulting state and the lease release, and names the underlying command (`iso_test off`). It is clear what the tool does, but it never distinguishes itself from sibling lifecycle tools like test_finish or release_host, which an agent must choose between.

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?

Usage is only implied: 'Dismiss a session' suggests end-of-test cleanup, and 'releasing a still-held host lease' hints at when it is applicable (a lease still held). There is no explicit when-to-use versus test_finish/release_host, and no stated exclusions or preconditions.

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