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

Annotations already declare readOnlyHint=false and destructiveHint=false. The description adds genuinely useful behavior beyond them: a code is generated at creation, nothing is sent to the client at this step, the tool 'runs without asking' (no confirmation), and it requires a Cotlet API key with app access. That is real added context, though the return shape and how the code is used are left implicit.

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 modes are front-loaded, but the description repeats itself: the first sentence already says 'the whole document, selected line items or a percentage,' and the second sentence restates 'the whole estimate, selected line items or a percentage of the total.' That redundancy costs space without adding 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 draft-creation tool with no output schema, the description covers what is created, that it stays undelivered until send_document, the auth requirement, and no-confirmation behavior. It does not describe the generated code's purpose or the draft's resulting state, but nothing critical for correct invocation 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 nonetheless adds meaning by tying the three operating modes (whole document, selected line items, a percentage of the total as progressive invoicing) to the three parameters, clarifying that percent and item_ids are mutually-scoped billing selectors against estimate_id.

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 (creates a draft invoice) and resource (from an estimate), and enumerates the three billing modes: whole estimate, selected line items, or a percentage. It also routes against the sibling houzz-pro_send_document for client delivery, so an agent can distinguish it from other houzz-pro invoice tools without reading 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?

Explicitly frames the workflow: this tool produces a draft and 'Nothing reaches the client until send_document,' which tells the agent when to use this versus the delivery sibling. It lacks an explicit when-not clause, but the draft-vs-send distinction is clear context.

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