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

With no annotations provided, the description carries the behavioral burden and discloses meaningful side effects: 'Clears Agree' and 'Does not run.' It also surfaces the write-tier approval flow and the distinction between from-now-on and just-once approvals. It does not fully describe reversibility or the impact on an existing contract beyond the force parameter, but it gives substantially more transparency than a bare mutation description.

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 dense but well organized: outcome, side effects, usage conditions, routing, and approval caveat each get their own concise line. There is no filler, and the most important facts are front-loaded before the approval note.

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?

Given the absence of annotations and an output schema, the description covers the critical context: what the tool transforms, when to use it, that it does not execute the Play, that it clears Agree, and what approval implications exist. The main gap is that it does not name the closest sibling alternative or describe the expected return value/verification step in detail, though it does mention calling get_playbook afterward.

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 all four parameters, including the 'force' behavior and the choice between tactic_id and tactic_title. The description adds no parameter-specific details beyond framing the input as 'one engine-drafted Play,' which is sufficient but not a meaningful improvement over 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 names a specific action and object: 'Rewrite one engine-drafted Play into an English operator contract (outcome, who, what Yes authorizes).' It also distinguishes itself from run_playbook by stating 'Does not run' and from get_playbook by framing itself as the step before 'then get_playbook.'

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 explicit invocation triggers: 'Use on first Focus view leftovers or when get_playbook still shows an activity slug as the title.' It also provides a routing sequence, 'Engine slug Play → English contract → use this, then get_playbook.' However, it does not explicitly state when to prefer this over the similar sibling redraft_engine_playbooks, so it stops short of a full when-not/alternative explanation.

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