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

Annotations declare destructiveHint=true and idempotentHint=true, but the description goes well beyond them: it states that omitted charges are archived, that product links outside productIds/charges are removed, that the deal amount/monthly revenue/currency are overwritten, and that draft commission lines are recalculated. It also spells out the exact idempotency retry behaviour and warns that CRM field values are untrusted data.

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 core action and its prerequisite are front-loaded, and most sentences carry non-obvious rules that an agent could not infer from the schema. It is dense and long, but the length is justified by 21 parameters and nested objects; a few clauses (e.g. the currency/millionths note) could be tightened.

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 destructive 21-parameter mutation with no output schema and nested objects, the description covers replacement semantics, archiving, side effects and idempotency. It does not state what happens on a stale expectedRevision conflict, the return shape, or any permission requirements, which are the remaining gaps.

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 only 5%, so the description carries the burden and does substantial work: it explains expectedRevision/expectedUpdatedAt sourcing, charges-as-complete-list semantics, commitment type meanings, the one-off vs recurring date split, millionths units, price period values, and idempotencyKey format. Several parameters (mrrMicros, contractLength, forecastMonths, revenueSharePercent, currencyChangeReviewed, legacyAdoptionReviewed, pricingMode) remain unexplained, so it falls short of full compensation.

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?

Opens with a specific verb and resource: 'Replaces a deal's pricing terms with a new revision.' This clearly separates it from the read-side sibling get_deal_commercials and from preview_catalogue_price, which the description later names as a related step.

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?

Explicitly names the prerequisite ('Read get_deal_commercials first and send its revision as expectedRevision and its updatedAt as expectedUpdatedAt') and ties catalogue conversion to repeating preview_catalogue_price. It also gives conditional rules for when FIXED vs UNSPECIFIED commitment applies and when charges may be omitted.

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