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

readOnlyHint=true already establishes the safety profile, and the description layers on useful context: which fields are returned, what free-text search covers, the filtermode semantics, and the upstream endpoint (GET /invoices). It omits pagination/rate-limit behavior, but the essential read-only semantics and result shape are disclosed.

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?

Purpose and returned fields are front-loaded, and the opportunity-filter tip is dense and high value. Some sentences duplicate schema content (search scope, filtermode enum values) and the trailing 'Current RMS: GET /invoices' is low-information, but overall the length is proportionate.

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, the description usefully states the returned fields, which an agent needs before calling a list tool. Given 8 params, a nested filters object, and no required args, the description covers the main retrieval paths; pagination/sort behavior is left entirely to the schema, which is acceptable since page/per_page/sort are documented there.

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 3 baseline applies, but the description adds meaning beyond the schema by giving a concrete filters recipe (invoice_items_source_type_eq=Opportunity, invoice_items_source_id_eq=<id>) combined with filtermode all, which the generic filters description does not explain.

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+resource ('List invoices and credit notes') and enumerates the fields returned (number, dates, status, totals), which is more than the title alone. It does not explicitly contrast with the list-vs-get sibling (current_rms_get_invoice), but 'List' vs 'get' makes the scope unambiguous.

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?

Provides concrete, actionable usage context: it names the free-text search fields and gives an exact filter payload for the non-obvious 'one opportunity's invoices' scenario with filtermode all. It stops short of when-not-to-use guidance or explicitly routing to current_rms_get_invoice for single-record lookups.

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