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

Beyond the annotations, the description discloses that no payment is created, that clientToken and idempotencyKey must be persisted before the call, and that registry/autonomy fields are unverified caller claims. These are meaningful behavioral and trust boundaries not visible from readOnlyHint, openWorldHint, or destructiveHint.

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, each carrying distinct information: no payment, required saves, caller-claims caveat. The most decision-relevant fact is front-loaded.

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 write operation with rich schema descriptions and idempotency annotations, the description plus schema largely covers correct invocation. The main gap is termsVersion: the schema only gives length constraints and the description never explains where it comes from or how it should be chosen.

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 75%, covering clientToken, idempotencyKey, and discovery. The description mostly restates those instructions ('Save... first') and its 'caller claims only' note adds little beyond the discovery schema's own caveat. termsVersion remains undocumented, and the description does not compensate.

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?

The title and description make clear the tool creates a run and explicitly states it creates no payment, distinguishing it from payment-related siblings like get_payment_quote. It does not explicitly contrast itself with poll_run or other run tools, so it stops short of a 5.

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?

The description gives practical prerequisites ('Save clientToken and idempotencyKey first') and warns that registry/autonomy fields are caller claims, which implies when care is needed. However, it never states explicit conditions for when to use this tool versus alternatives, nor names any excluded cases.

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