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

With zero annotations the description carries the full burden and does add real behavioral context: it merges rather than replaces (preserving cost center and unedited fields), it defaults to a non-committing preview, and it will not silently enable automation. What it omits is the concurrency/permission story implied by expected_revision and operation_key, and what a failed merge looks like.

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?

Two tight sentences with the merge guarantee front-loaded and no filler. The compound 'Read/merge/edit' is slightly hedged phrasing, but nothing 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 7-parameter mutation with a nested object, no annotations, and no schema descriptions, the description is too thin — an output schema covers return values, but the agent still cannot tell what 'kind' accepts, how expected_revision interacts with the write, or what operation_key is for.

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% across 7 parameters (including a free-form nested 'changes' object), so the description must compensate. It only obliquely touches dry_run ('Default preview') and the preservation semantics relevant to 'changes'; kind, rule_id, company_name, expected_revision, and operation_key are never mentioned, leaving the agent to guess at revision-conflict and idempotency behavior.

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 verb set ('Read/merge/edit') and the merge-not-replace semantic are specific enough that an agent knows this is a partial-update tool rather than a create/delete. However, it says 'a rule' rather than 'an AI booking rule', so the resource is only identified by the tool name, and differentiation from update_bank_transaction_booking_rule / update_accounting_booking_rule comes from the name alone.

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?

'Default preview' implies the intended preview-then-apply workflow and hints that dry_run must be turned off to commit, which is useful implied guidance. But there is no explicit statement of when to use this versus create_ai_booking_rule, clone_ai_booking_rule, plan_ai_booking_rule_batch, or the activation tools (set_ai_booking_rule_auto_booking / explicit_enable_bank_rule_auto_booking), and no prerequisites or conflict-handling advice.

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