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

The description explicitly claims 'This tool NEVER writes', but the annotations declare readOnlyHint=false. This is a direct contradiction with the annotation. Additionally, the description itself says 'A new proposal replaces the workspace's pending one,' which implies a write to workspace state. Because the description contradicts the annotations, it fails behavioral transparency.

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 information-dense. It front-loads the core purpose, then adds the critical non-write caveat, the proposal flow with companion tools, and behavior for questions vs. changes. Every sentence contributes useful operational context without padding.

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 present, the description adequately covers return behavior: an assistant message, a proposalId when a change fits, no proposal for questions, and replacement of pending proposals. It also notes the LLM call. Minor gaps like error cases or response formatting keep it from a 5, but the essentials are present.

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 100%, so the schema already documents both parameters well. The description adds some value by framing the request as plain-language instructions and by explaining that workspaceId is key-bound for workspace keys, but it does not meaningfully extend beyond what the schema already provides.

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 clear, specific action: asking the playbook assistant for a change to craft data and receiving a proposal. It distinguishes itself from related sibling tools by naming campaignstack_get_playbook_proposal and campaignstack_decide_playbook_proposal as the follow-up tools for reading and applying the 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?

The description gives concrete usage context: ask for a change, get a proposal; questions get answers without proposals; new proposals replace pending ones. It also explains the workflow with companion tools. It does not explicitly state when to use an alternative instead, but the boundary is clear enough for an agent.

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