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

Annotations already declare the safe read-only, open-world profile. The description adds real beyond-schema context: newest-first ordering, 100-per-page paging, that items carry approved/draft status, the external-vs-internal document-number distinction, and that a Cotlet API key with app access is required. Minor flaw: it refers to 'next_cursor' while the input parameter is named 'cursor'.

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?

Reasonably front-loaded but redundant: 'newest first' appears twice and the first two sentences overlap heavily (purchase invoices/expenses with supplier/total/due date vs. lists purchases from the Expenses section). Trimming would tighten it without losing meaning.

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?

Given read-only annotations, no output schema, and an empty-required 5-param input, the description is nearly complete for an agent: it explains return fields, ordering, paging, item status, and auth. The only gap is the 'next_cursor'/'cursor' naming mismatch, which could briefly confuse pagination.

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%, so the schema already documents all five parameters. The description restates document_number semantics ('the supplier's own number') and paging, but adds little that is not already in the schema, so it sits at the baseline.

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 (list) and resource (purchase invoices/expenses) and pins the scope to the Expenses section, which separates it from holded_list_invoices (sales side) and holded_create_purchase. It also names the fields returned (supplier, supplier document number, total, due date).

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?

Offers one practical usage hint ('search by supplier document number to detect a bill you already recorded'), but never names an alternative tool or states when NOT to use this versus holded_list_invoices or a future get-purchase tool. Usage is implied rather than guided.

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