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

Beyond the annotations (write, non-destructive, non-idempotent), the description discloses consequential behavior: the draft has no number until issued, VAT is auto-applied from business settings at 15% or 0%, prices are pre-VAT, and it returns computed totals plus a review link. The main gap is that it does not warn that repeat calls create duplicate drafts (idempotentHint is false) and says nothing about auth or account-connection requirements.

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 compact sentences with the most decision-relevant fact (draft, not issued) front-loaded, followed by the tax rule and the return shape. Nothing is redundant and no sentence could be dropped without losing agent-relevant information.

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 three-parameter mutation tool with no output schema, the description covers the creation semantics, tax behavior, and return values, and the annotations cover the safety profile. What is missing is how the customer is resolved (existing customer vs free-text name) and duplicate-retry behavior, which matter for correct invocation.

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%, so the schema already documents customer, items, and note, including that unit_price is pre-VAT. The description reinforces the VAT/unit-price semantics, which is useful but largely duplicative, and it adds nothing about the optional note or about quantity constraints. Baseline 3 applies when the schema does the heavy lifting.

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 ('Create a DRAFT invoice') plus the account it lands in, and the emphasis on DRAFT with 'It is NOT issued' immediately separates it from any issuing/payment workflow implied by list_unpaid_invoices. An agent can distinguish this from all three siblings without opening a 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?

The description clearly frames the use case and an important exclusion: this tool never issues the invoice, the user does that in the Fatoorati app. That is real routing guidance for an agent deciding whether to call it. It stops short of naming siblings (e.g. use search_customers to resolve the customer) or stating prerequisites such as the customer needing to exist.

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