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

Beyond the readOnly/idempotent annotations, the description discloses important behavior: pending requests remain unchanged, approval-scope confirmation is required, and the call returns both a preview and an expiring five-minute token without applying the change. The unexplained 'Named-person chain routing uses IPP' and vague 'approval-scope confirmation' keep it from being fully transparent, but the core side-effect profile is clear.

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 short and front-loads the action ('Prepare a sparse change') before constraints and return behavior. Most sentences earn their place, though the unexplained IPP sentence is jargon that may not help an agent decide or invoke correctly.

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 preview tool with a complex nested schema and no output schema, the description covers the essential contract: what is previewed, what is returned, that a confirmation token expires in five minutes, and that nothing is applied. It is still missing explicit guidance on how to apply the token afterward and does not describe the preview payload structure, but it is largely complete for correct invocation.

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 0%, so the description must carry the burden. It adds two useful semantic hints: 'exact approval rule' implies the rule_id must identify a single rule, and 'sparse change' implies a partial patch rather than full replacement. It does not explain the nested patch fields such as conditions, chain_steps, or required_approver_role, leaving meaningful gaps for a complex nested input.

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 gives a precise verb and resource ('Prepare a sparse change to an exact approval rule') and immediately clarifies the preview boundary ('it does not apply the change'). This distinguishes it from the sibling update_approval_rule and other preview tools without requiring the schema to be opened.

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 implies a two-step preview-then-apply workflow by mentioning a five-minute confirmation token and stating that the change is not applied. However, it never explicitly names update_approval_rule as the tool to use with that token, nor does it state when this preview is mandatory versus optional, leaving the agent to infer the workflow.

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