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

Annotations already indicate destructive and idempotent behavior, but the description adds meaningful detail: removal is forward-only, queue routing to the agent is unrouted in the same change, and live/historic revisions cannot be modified. This goes well beyond the structured annotations.

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 sentences, each carrying necessary information: the primary action, the side effect, and the immutability constraint. No filler or 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?

For a mutation tool with no output schema, the description covers the core operation, the side effect, and the critical constraint on which revisions are valid. An agent has enough information to invoke it correctly without guessing.

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 descriptions are minimal ('Agent ID', 'Revision ID', 'Automation ID'), but the description clarifies that revision_id must refer to a draft revision and that agent_id refers to an agent present in that draft. This adds semantic 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?

The description clearly states the verb and resource: remove an agent from a draft revision. It adds the 'forward-only' qualifier and notes the queue-routing side effect, which distinguishes this from sibling tools like removeAutomationAgent or removeAutomationRevisionQueue.

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 makes the key usage boundary explicit: live and historic revisions are immutable, so this tool is for draft revisions only. It does not explicitly name alternative tools for adding or replacing agents, but the context is clear enough for an agent to decide when to use it.

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