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

It discloses important behaviors beyond annotations: the tool never directly applies craft-data changes, returns either an answer or a proposalId, replaces any existing pending proposal, and runs an LLM call. The phrase 'NEVER writes' could be read too literally, but the following sentence about replacing the pending proposal clarifies the real state mutation, and readOnlyHint=false is consistent with that.

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?

Five sentences, all carrying operational value: main action, non-write behavior, follow-up workflow, question edge case, and pending-proposal side effect. It is front-loaded and contains no filler.

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?

With no output schema, the description still tells the agent exactly what to expect as output, what to do next with the proposalId, what happens to a pending proposal, and what happens if the request is a question. Nothing needed to call it correctly is missing.

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 100%, with both parameters already described: request has min/max length and examples, and workspaceId has a default behavior. The description adds no significant new parameter-level meaning, so the baseline of 3 is appropriate.

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 states a specific verb ('Ask the playbook assistant') and a specific resource ('the workspace's craft data'), and clearly defines the outcome: a proposal with a proposalId, not a direct change. It also names the related reading and applying tools, which distinguishes it from campaignstack_get_playbook_proposal and campaignstack_decide_playbook_proposal.

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?

It gives explicit routing for the proposal workflow: read with campaignstack_get_playbook_proposal, apply with campaignstack_decide_playbook_proposal, and explains the question-without-proposal case. It does not explicitly contrast this with related playbook tools like regenerate_playbook or revert_playbook, so it is clear but not exhaustive.

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