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

Annotations already cover the safety profile (readOnlyHint true, destructiveHint false, openWorldHint true), and the description adds real context on top: status semantics ('Open includes partially paid invoices'), the filter meanings, the page cap of 100 invoices, and an explicit auth requirement ('Cotlet API key with access to this app'). It stops short of a 5 because it says nothing about response shape or how cursor pagination terminates.

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 description is short and front-loads the resource and returned fields before moving to enum semantics and auth. The sentence 'Lists invoices the way the Invoice list does' largely restates the opening sentence and leans on a UI reference, which is the one piece of unearned length.

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?

With no output schema and a fully documented parameter set, the description supplies what is missing: pagination page size, filter semantics, status semantics, and the API-key prerequisite. An agent has enough to call it correctly, though the absence of any note on total counts or result ordering leaves a minor gap.

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 baseline is 3, and the description earns above that by explaining enum semantics the schema only lists: what Open includes, what past_due means, and what unsent means. It does not touch limit, cursor, due_before or customer_id, but those are already self-documenting in the schema.

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 names the concrete resource and the fields returned (status, amount due, due date, last send date), so an agent knows this is a read-list tool for Housecall Pro invoices. It does not name any sibling (e.g. housecall-pro_get_invoice) to sharpen the boundary, and the phrase 'Lists invoices the way the Invoice list does' is partially circular, so it falls short of a 5.

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?

It gives useful filter-level guidance ('Use filter past_due for invoices not paid by their due date, or unsent for Open invoices with no send record'), which implies how to use the tool. However, it never states when to choose this tool over housecall-pro_get_invoice or other list tools, and gives no exclusions or preconditions beyond the auth note.

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