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

With annotations only declaring a generic write profile, the description adds concrete side effects: the estimate stays in the list but its status changes from pending to approved, a new invoice is created with all estimate data, and no client notification occurs. It also names the auth requirement (Cotlet API key with app access) — rich context well beyond the 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?

Front-loaded and informative, but it restates the same idea three times ('generate an invoice with everything from the estimate', 'the new invoice carries all the information from the estimate', 'does what Generate Invoice does in Joist'). The redundancy costs it conciseness points.

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?

No output schema exists, and for a 1-param conversion tool the description covers the important outcomes (new invoice, estimate status change, unsent state) plus auth. It's essentially complete, with only minor gaps about the created invoice identifier or how to retrieve it afterwards.

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% and the single parameter (estimate_id) is documented as coming from list_estimates in the schema. The description adds no syntax or format detail, so the schema carries the burden and the baseline of 3 applies.

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?

Names a specific verb+resource (generate an invoice from an estimate) and clearly scopes it as a conversion that pulls all estimate data. An agent can distinguish it from siblings like joist_create_estimate and joist_send_document without opening any 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?

States the key routing condition: the invoice is not sent until joist_send_document is called, and nothing goes to the client, so 'it runs without asking.' That effectively differentiates it from the send tool, though it doesn't explicitly enumerate when to prefer this over other creation paths.

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