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

Beyond the annotations, it reveals important behaviors: omitted charges are archived, missing revenue dates leave components unallocated in reports, fixed-term end dates are inclusive and derived when omitted, amounts are in integer millionths, and idempotencyKey must be a UUID. It also flags CRM field values as untrusted data, adding security-relevant behavior. This does not contradict the readOnlyHint=false or destructiveHint=false 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 long but densely packed with high-value information, with the core action front-loaded and each sentence adding a distinct constraint or behavioral fact. The length is justified by the tool's complexity (21 params, nested objects) and no sentence is 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?

It covers the most critical behavioral aspects—concurrency, archive behavior, commitment, revenue scheduling, currency amounts, idempotency, and security—making it possible for an agent to call the tool correctly in common cases. Gaps remain: pricingMode values are not explained, workspaceId's multi-workspace requirement is not mentioned, and there is no note about return values (though no output schema exists to offset this).

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?

With only 5% schema description coverage, the description carries the parameter-semantics burden and does so extensively for key fields: charges replacement semantics, commitment type constraints, oneOffRevenueDate vs recurring date behavior, price interval restrictions, and idempotencyKey format. However, some required parameters such as pricingMode, dealId, and a few optional fields like revenueSharePercent or forecastMonths are not explained, so it is not exhaustive.

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 opens with 'Save a deal's commercial terms through Anvil's commercial service,' naming a specific verb, resource, and service. It clearly differentiates from the sibling get_deal_commercials by being the write counterpart and from update_workspace_commercial_settings by targeting deal-level terms.

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?

It explicitly instructs the agent to 'Read get_deal_commercials first and send its revision and updatedAt,' establishing a precondition and source for required optimistic-concurrency fields. It also gives conditional guidance for charges ('leave charges out to keep the saved breakdown') and references preview_catalogue_price for conversions, making the choice of inputs and prior calls explicit.

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