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

The description discloses non-obvious behavior: saved rules wait for user approval and only apply after approval, and it adds the safety-relevant detail that rules never change access permissions or confirmation requirements. The destructiveHint annotation is not explained in terms of specific side effects, but the description still adds meaningful behavioral context beyond the annotations.

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 front-loaded, with each sentence earning its place: the main purpose, an example, the approval workflow, the stated_by_user distinction, and the safety reassurance about permissions. There is no filler or repetition.

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 7-parameter tool with good schema coverage and no output schema, the description plus schema is nearly sufficient: it covers what the tool does, examples of supported rule kinds, and the crucial approval-gated behavior. It lacks explicit guidance on what the agent should do after the save completes, but that is a minor gap.

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 already high (86%), so the schema does most of the parameter documentation work. The description adds useful semantic color, such as the categorization example linking a payee to an expense account and the clarification of stated_by_user. It does not deeply explain the nested matcher/outcome objects beyond what the schema 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 specific action "Save a user's bookkeeping preference for a connected company" and enumerates the kinds of rules it covers (categorization, vendor fact, preference, procedure). It clearly identifies the resource (rules) and gives a concrete example. It does not explicitly differentiate it from sibling tools like list_rules or retire_rule, so it stops short of 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?

The description conveys the relevant context: use this tool when a user states a bookkeeping preference, and it instructs the agent to mention the approval requirement on the Caribooks Rules page. It does not explicitly state when not to use this tool or point to alternative tools, so it lacks the exclusion guidance needed for a 5.

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