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

The description discloses that the tool mutates state (starts the run), returns a receipt with new status, and enforces optimistic concurrency via expected_version. It adds meaningful behavior beyond annotations (idempotentHint, readOnlyHint=false) by explaining the locking mechanism and the refusal condition.

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?

Four sentences, no filler. The purpose is front-loaded, the concurrency behavior is explained in the middle, and the usage condition closes it. Every sentence adds value, including the example which is compact and illustrative.

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 tool with two parameters and no output schema, the description covers the purpose, the precondition for use, the critical parameter semantics, and the return value. It is complete enough for an agent to know when and how to invoke it correctly.

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 0%, so the description carries the burden. It explains expected_version's purpose and usage with an example, and run_id is self-evident as a UUID. However, run_id is not explicitly described, though its role is obvious from context. The example clarifies the JSON shape.

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 description clearly states a specific action: 'Authorizes the spend a held run was projected at, and starts it.' It identifies the resource (a held run) and the outcome (starting it), and it is distinct from siblings like start_run and cancel_run by the authorization precondition.

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?

Explicit guidance is given: 'Only call this after a person has seen the projected cost and agreed to it.' It also instructs to pass expected_version from get_run to prevent stale authorization, which is a concrete usage rule. Though it doesn't name alternative tools, the condition is unambiguous.

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