create_approval_rule

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

Annotations already indicate this is a write operation (readOnlyHint=false) and non-idempotent. The description adds valuable context beyond those annotations: the automatic generation of approval requests, the WRITE_ENABLED=true requirement, and the use of the sysapproval_rule table. This gives the agent a better sense of side effects and prerequisites without contradicting 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 two sentences, front-loaded with the primary purpose, followed by the permission requirement and table detail. Every word earns its place; there is no redundancy or filler.

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 tool's moderate complexity (7 params all documented, write operation) and the presence of annotations, the description covers the essential behavioral context: what the tool does, a key prerequisite, and the storage table. It does not describe return values, but the lack of an output schema makes that less critical. A small omission is not explicitly mentioning that 'condition' blank means always fire, but that is present in the schema.

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?

The input schema has 100% coverage with each of the 7 parameters described. The description does not provide additional parameter-level detail beyond what the schema already states (e.g., it references 'conditions' which maps to the 'condition' field, but that field is already described as 'Encoded query that determines when the rule fires'). With high schema coverage, a baseline of 3 is appropriate.

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 ('Create an approval rule') with a precise behavioral outcome ('automatically generates approval requests when a record matches given conditions'). It distinguishes this tool from siblings like approve_request or create_flow by focusing on rule creation rather than individual approval or flow automation.

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 clearly implies when to use the tool: when a user needs to set up an automated approval rule based on record conditions. It also notes a prerequisite (WRITE_ENABLED=true) and mentions the underlying table, which aids in context. However, it does not explicitly name alternatives or exclusions (e.g., 'use create_flow for complex routing'), so it stops short of a 5.

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