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

Annotations already declare readOnlyHint=true, openWorldHint=true, and destructiveHint=false, so the safety profile is covered. The description adds essentially nothing beyond that – no ordering, whether partially paid invoices are included, or how much data volume to expect; the SOAP endpoint name ('GetInvoices_Unpaid') is implementation trivia rather than agent-useful context.

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?

Two short fragments with zero padding, and the key scope phrase comes first. The trailing 'paged here' and SOAP method name are slightly awkward but not wasteful enough to drop below a 4.

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 should say something about what a returned invoice contains or its ordering. It covers the filter and pagination adequately, but an agent still can't tell what it gets back or how results are sorted, leaving a clear gap for a tool with this many near-duplicate siblings.

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%, with both limit and offset fully documented including defaults and maxima, so the schema does the heavy lifting. The description only says 'paged here' and adds no meaning about page semantics or what happens at the boundaries, so the baseline 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?

States the resource (sales invoices) and the filter (not yet paid in full) with implied list verb, so an agent knows what it returns. However, it does nothing to distinguish itself from close siblings like kashflow_list_overdue_invoices, kashflow_list_invoices, and kashflow_list_recent_invoices; the unpaid-vs-overdue boundary is left for the agent to guess.

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 guidance on when to choose this over list_overdue_invoices or list_invoices, and no exclusions or preconditions. The only usage-adjacent phrase is 'paged here', which signals pagination but not selection criteria.

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