test_start

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

Annotations already declare this is a non-idempotent, non-destructive mutation, and the description adds two non-obvious behaviors: that passing a host claims a host lease, and that the agent must itself mirror state onto the in-game TEST STATUS HUD via `iso_test start` over netcon. The external follow-up action is the kind of context annotations cannot convey. What is missing is behavior when a session is already running, given idempotentHint=false.

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 short sentences with the purpose front-loaded and no filler. The third sentence is the most valuable and could have been placed more prominently, and the inconsistent indentation slightly hurts scanning, but there is no wasted text.

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 only needs to carry session lifecycle and host-lease semantics — which it does, including the out-of-band HUD mirroring requirement. The remaining gap is concurrency/duplicate-start behavior for a tool flagged as non-idempotent.

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 coverage is 100%, so the baseline is 3, but the description earns a bump by explaining the consequence of host_id (a lease is claimed) rather than just restating 'Host to claim for the session'. The netcon/HUD sentence also clarifies the practical role of the name label.

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 ('Start a server-side test session') plus the resulting state ('state=running'), which separates it from test_finish/test_step/test_status implicitly. It never names a sibling explicitly, so differentiation is inferable rather than stated.

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 implied — you start a session, and the conditional 'Claims the host lease when a host is given' hints at when to pass host_id. There is no explicit statement of when to call this versus test_finish, test_step, or list_test_runs, and no prerequisite/exclusion guidance.

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