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

Annotations only say destructive/idempotent; the description goes well beyond them by disclosing the cost model (spends workspace budget, every attempt metered, voice attempts also pay synthesis and transcription) and by explaining that the required idempotency_key is what makes a retry safe rather than a second paid run. This is exactly the extra context annotations cannot carry.

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 tight sentences with the cost warning front-loaded, then the alternative, then the retry-safety rule for the required key. No filler and no repetition of the title.

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?

No output schema, and the description covers what matters most for a costly mutation: spend behavior and retry safety (partially describing the return, i.e. the same run comes back). It does not cover pinned_source semantics or failure behavior, so a small gap remains for a 6-parameter tool.

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%; the description reinforces idempotency_key semantics but that parameter already has a thorough schema description, and agent_id, suite_id, and pinned_source get no meaning from either source. Baseline 3 is appropriate given the schema does part of the work and the remaining gaps are mostly self-explanatory identifiers.

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 run of a simulation suite') and implicitly separates itself from the sibling family (preview/cancel/get_simulation_run) by naming preview_simulation_run as the non-starting alternative. An agent can place this tool without opening a 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?

Names the alternative (preview_simulation_run) and its distinguishing condition ('returns the estimate without starting anything'), which is strong routing guidance. It does not spell out an explicit when-not-to-use or a prerequisite ordering (e.g., 'preview first'), so it falls just short of the top band.

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