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

Adds real context beyond the single destructiveHint annotation: the mutation profile ('MUTATES Quaderno data'), the side effect of automatic tax calculation and document generation, the underlying endpoint (POST /transactions), and the return shape (created invoice/credit-note). It does not cover idempotency or error behavior, but the annotation bar is already partly met.

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?

Front-loads the mutation warning before the mechanics, and each sentence carries a distinct piece of information (type semantics, required inputs, escape hatch, endpoint, return). The parenthetical field list is long but is the substantive payload of the escape-hatch guidance, not 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?

For a six-parameter, nested-object mutation tool with no output schema, the description covers mutation semantics, required vs optional inputs, the escape hatch, the HTTP endpoint, and the return value. Nothing an agent needs in order to call this correctly is missing.

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 the baseline is 3; the description goes further by naming the non-typed attributes the `fields` escape hatch is intended for (date, currency, shipping_address, evidence, processor, exchange_rate, tags, custom_metadata), which the schema's generic 'additional raw Quaderno fields' does not spell out. It also clarifies that items are the required core and payment/customer are the expected companions.

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 ('record a sale or refund transaction'), names the type enum values, and discloses the downstream effect (Quaderno computes tax and produces the compliant document). An agent can distinguish this from quaderno_create_invoice or quaderno_calculate_tax without opening the schema.

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?

Tells the caller what to supply ('Provide the customer, items, and payment') and routes any untyped attribute into `fields` with a concrete enumeration of examples. It does not explicitly state when to prefer this over quaderno_request or quaderno_create_invoice, so it falls short of full alternative routing.

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