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

The description contradicts the annotations: it states 'Idempotent per call' while idempotentHint is declared false, a direct conflict on repeat-call semantics. The otherwise rich disclosure (public-internet exposure matching openWorldHint=true, non-destructive, non-read-only, ttl bounds, capacity/billing effects) is undermined by this inconsistency.

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?

Front-loaded with the core action, then layers effects and caveats; each sentence carries real information. It is dense and slightly packed, but there is no filler.

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?

For a create tool with no output schema, it covers the important unknowns: what resources are created, their lifetime bounds, the public-internet side effect, and the billing/capacity accounting. It does not describe the returned run identifier, but the coverage is otherwise strong.

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 50%, so the description must compensate. It restates the ttl range/default that the schema already documents ('its ttl, default 30m, at most 24h') and adds nothing for the undocumented 'reason' parameter, so it adds little meaning beyond the schema.

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?

Specific verb + resource ('Start a run of a suite's current version') and it enumerates exactly what is allocated (inbox addresses, callback/mock URLs, route labels). An agent can distinguish this from rig.run.finish, rig.run.cancel and rig.run.get without opening any schema.

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?

Provides clear operational context and effectively routes the agent onward with 'Finish the run when done rather than letting it expire' (rig.run.finish). It does not explicitly name the finish/cancel siblings or state when not to start a run, so it stops short of full when/when-not guidance.

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