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

Annotations declare destructiveHint=true, so the agent expects a write. The description adds the crucial nuance that this is a soft deactivation – the rule stays in history but is no longer active – which reframes how 'destructive' this actually is, plus the pending-approval edge case. It omits auth/permission requirements.

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?

Three sentences, front-loaded with the core action, then the state effect, then the edge case. The embedded Approvals URL is slightly bulky but serves a real routing purpose, so little is wasted.

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 two-parameter mutation with no output schema, the description covers the state outcome and the one notable exception case. Missing only permission/auth expectations, but the essential calling information is present.

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 rule_id and company are already documented in the schema. The description only echoes 'by id' without adding format or sourcing detail beyond what the schema's 'as shown by list_rules' already provides. Baseline 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?

States a specific verb (retire), resource (bookkeeping rule), and scope (active rules, by id). This clearly separates it from siblings like remember_rule (create) and list_rules (read), and the 'no longer active / remains in history' framing pins down the exact operation.

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?

Gives an explicit when-not: a rule still waiting for approval must be handled in Caribooks Approvals, not here. It also frames the action as following the user's request. It stops short of naming a sibling alternative for reversing or fully deleting a rule, so it is clear context but not complete routing.

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