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

Despite annotations already covering destructive and idempotent behavior, the description adds substantial context: an allowlisted action-type restriction, Startup-or-higher entitlement, both read and write consent, a stable idempotency key, exact-intent confirmation, and concurrency guidance via the current revision. This goes well beyond what the annotations provide.

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?

The description is compact and front-loaded: the first sentence states the purpose, the second scopes the allowed actions, the third lists prerequisites, and the fourth gives revision guidance. Every sentence adds distinct, useful information without redundancy.

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?

The tool is destructive, idempotent, and has a nested input schema with no field descriptions, so the description needs to do a lot. It covers safety, scope, entitlement, idempotency, confirmation, and revision semantics, and an output schema exists so return values need not be explained. It still leaves project_id and target_id semantics implicit, preventing a perfect score.

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 0%, so the description must carry parameter meaning. It adds useful semantics for idempotency_key ('stable'), confirmation ('exact-intent confirmation'), and expected_version ('current revision'). But it does not explain project_id, target_id, or the payload structure, leaving clear gaps for a four-parameter tool with nested inputs.

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: 'Execute an existing approved internal action using its current revision.' It also narrows the allowed action types, which helps distinguish it from generic action tools. However, it does not explicitly name sibling alternatives like founder_ops.approve_action or founder_ops.retry_action, so it falls short of full sibling differentiation.

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 context for when this tool applies: only approved internal actions, only stored allowlisted task/monthly-close/evidence actions, and only with the right entitlement and consent. It also gives operational guidance to read current state and use the current revision. It does not name alternative tools or state when not to use it, so it lacks explicit exclusions.

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