add_playbook_ruleAdd a piece of guidance to the context document the AI agent reads before every answer (Agent training → Context). It goes under the answers your team approved. Keep it general and do not copy help center articles: the agent already searches them. Admins only.
| Name | Required | Description | Default |
|---|---|---|---|
| content | Yes | The guidance, up to 12,000 characters. | |
| productId | No | Not needed: a workspace has one context. |
Changes observed during successful MCP inspections.
Input schema / properties / content / descriptionPrevious value: -"The rule, up to 12,000 characters."New value: +"The guidance, up to 12,000 characters."Input schema / properties / productId / descriptionPrevious value: -"Product id from list_products."New value: +"Not needed: a workspace has one context."Input schema / requiredPrevious value: -[
- "productId",
- "content"
-]New value: +[
+ "content"
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations cover the safety profile (readOnlyHint=false, destructiveHint=false), and the description adds substantial context beyond them: the content is read before every answer, it lands under approved answers, and the call requires admin rights. It does not say whether an add is append-only or whether duplicate guidance is rejected.
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?
Four short sentences, front-loaded with the core action and impact, then placement, then content constraints, then the auth caveat. No filler; each sentence changes how an agent would call the tool.
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 one-required-string mutation with annotations and no output schema, the description covers what is written, where it goes, how it is used, and who may call it. The remaining gap is behavioral detail about duplicate or conflicting rules, which is secondary.
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%, so both parameters are already documented, including the deliberate exclusion of productId with a reason. The description adds only a loose gloss on 'content' as 'a piece of guidance' and does not restate the 12,000-character limit or format expectations. Baseline 3 applies when the schema carries the parameter burden.
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: 'Add a piece of guidance to the context document the AI agent reads before every answer', plus the UI location. It never names its sibling update_playbook_rule to mark the add-vs-edit boundary, which is the one thing that would push this to a 5.
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?
'Keep it general and do not copy help center articles: the agent already searches them' is an explicit negative-use rule with a reason, and 'Admins only' is a stated prerequisite. What is missing is any pointer to update_playbook_rule for editing existing guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.