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

With annotations already declaring readOnlyHint=false and destructiveHint=true, the description adds substantial context: the rule is inert until approved in Caribooks Approvals (with a URL), it is company-specific business data, and it never changes access permissions or confirmation requirements. Minor residual tension: it never explains why the tool is flagged destructive, and there is no mention of duplicate/idempotency behavior.

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?

Five sentences, front-loaded with the save action and scoped immediately; every sentence carries either scope, workflow, or permission semantics. Slightly long, and the stated_by_user sentence is partly redundant with the schema, keeping it from a 5.

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 mutation tool with nested matcher/outcome objects and no output schema, the description covers the essentials an agent needs: what is stored, that approval is required, and that the data is company-scoped and non-privileged. It leaves the agent guessing about the return value and about what happens on repeated saves.

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 86%, so the schema already carries most parameter meaning and baseline is 3. The description adds a cross-parameter illustration of how kind, matcher, and outcome combine (payee → expense account) and clarifies that rules are company-scoped, though its stated_by_user sentence largely repeats the schema description verbatim.

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 and resource ('Save a user's bookkeeping preference... a categorization, vendor fact, preference or procedure') and enumerates the four rule kinds, which lets an agent distinguish it from siblings like list_rules, retire_rule, and update_preferences. The concrete example ('a categorization can associate a payee with an expense account') pins down what a saved rule actually is.

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 clear context for invocation (capturing a user's stated or inferred bookkeeping preference for a connected company) plus an operational directive: the rule is approval-gated, so the agent must tell the user. It does not name an alternative tool or state when NOT to use it, so it stops short of full when/when-not routing.

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