Brand book: lane, voice rules, banned words, goals — persistent across sessions

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

The description adds behavioral details beyond annotations, such as 'set (merge)' indicating merge semantics, and notes that banned words are 'flag[ged]' by draft_check and publish. It also mentions persistence and local/free attributes. These go beyond the boolean annotations (readOnlyHint:false, idempotentHint:true, destructiveHint:false) without contradiction.

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 three sentences long yet packs in free/local, persistence, the list of constraints, relationships to other tools, and the three actions. Each clause adds value, and the structure flows from high-level purpose to specific actions. No wasted words.

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 tool with nested goals and multiple arrays, the description covers the main aspects: what the brand book contains, that it persists, and the three actions. It does not describe the return format of 'check', but with no output schema required and the low-level schema having moderate documentation, this is acceptable. The description is largely complete for an agent to understand when and how to use the tool.

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?

With schema coverage at only 38%, the description compensates by explaining the 'set (merge)' behavior, the roles of banned words and goals (e.g., 'followers by date, originals per week'). It also clarifies that 'check' takes a draft as input, mapping to the 'text' parameter. This adds meaning beyond the raw schema properties.

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 tool manages the 'account's operating constraints' including lane, voice, banned words, and goals, and lists explicit actions (get, set, check). It distinguishes itself from siblings like draft_check and publish by positioning itself as the persistent brand book that those tools reference. This is a specific verb+resource with clear scoping.

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?

Context is provided that the brand book is used by 'draft_check and publish' and that goals are tracked by 'insights/report'. The description implies when to use this tool (e.g., to set or check brand constraints) but does not explicitly state when-not or mention alternatives. It gives clear context without exclusions, so a 4 is appropriate.

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