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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, so the safety profile is covered externally. The description adds real value by disclosing the pagination contract ('One page', page defaulting to 0) and the underlying endpoint, but says nothing about result volume limits, sorting, or what the response looks like.

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?

At three short sentences it is compact and front-loads the resource description. The middle sentence 'One page (page defaults0)' is malformed (missing space, awkward phrasing) and the trailing 'GET /invoices' is a raw endpoint dump that adds little for an agent that cannot issue HTTP directly.

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 seven optional parameters, 29% schema coverage and no output schema, the description leaves significant gaps: no pagination semantics beyond a default page, no indication of which filters combine or are ignored, and no sense of the return payload. For a list tool that an agent must page through, this is under-specified.

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 only 29% (only from_date/to_date are documented), so the description has to compensate. It partially does: it clarifies that keyword searches invoice numbers and customers, that status relates to paid status, and that page defaults to 0. But pagesize, payment_method and the interplay between page and pagesize remain completely unexplained in both schema and description.

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 conveys that this returns invoice records with totals, paid status and balances, and names the endpoint (GET /invoices), so the resource is identifiable. However, it never states plainly that it lists invoices, and 'Search invoice numbers and customers' is ambiguous about whether customers are a searchable field or a returned entity. Nothing distinguishes it from siblings like repairdesk_get_invoice or repairdesk_get_invoice_due.

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?

There is no when-to-use guidance at all: no statement about choosing this over repairdesk_get_invoice (single invoice) or repairdesk_get_invoice_due. The only usage-adjacent remark is 'One page (page defaults0)', which is pagination behavior rather than tool selection guidance.

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