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

Beyond the sparse annotations (idempotentHint=true, destructiveHint=false), the description reveals a rich behavioral contract: partial input is allowed, the response contains missing fields and a follow-up question, the access_token is the only handle for the order, and payment is deferred until the payment link is followed. This is precisely the kind of workflow context an agent needs to invoke the tool correctly and is not available from the schema or 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?

Four short, information-dense sentences with zero fluff. The front-loaded first sentence states the core action, followed immediately by the most important behavioral constraint (partial data allowed), then the access_token guidance, then the payment-state note. Every sentence earns its place and the structure is easy to scan.

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?

Given there is no output schema, the description properly conveys essential return semantics: missing fields, a next question, and the access_token. It also clarifies the payment status, which is critical for the agent's next actions. However, it does not explicitly indicate how to proceed after receiving the missing fields (e.g., calling update_certificate_order), leaving a small gap in the broader workflow context.

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 100% — every parameter is already explained, including enum values for property_type, the role of idempotency_key, and the scope of doors/windows/fields. The description adds only the general note that all data is not required, which is already apparent from the single required property in the schema. Per the coverage baseline, the description does not need to compensate further.

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 starts with a concrete verb-resource pair: 'Tworzy zamówienie świadectwa charakterystyki energetycznej' (creates an energy performance certificate order). It further distinguishes this tool by immediately stating that it accepts partial data, returns missing fields, and issues a unique access_token — none of which is true for siblings like create_draft or calculate_certificate_price.

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?

The description gives clear usage context: it explicitly says the tool can be invoked with incomplete data and that the resulting access_token must be carried into other tools. It also notes the order is unpaid until the get_payment_link link is used)Skip the exact phrase 'when not to use'; however, it does not mention alternatives or exclusions, so it drops just short of a 5.

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