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

Annotations already declare readOnly/openWorld/non-destructive, so the safety profile is covered. The description adds real value beyond that: it states no PDF/XML export, that results include both header and position lines, and it decodes the status codes (0 new, 10 to be posted, 20 open, 30 dunned, 40 settled, 100 deleted), which is behavioral detail absent from the annotations.

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?

Three sentences, each earning its place: the first covers scope and filters, the second the returned shape, the third the read-only/no-export boundary. Front-loaded with the identifying verb and resource.

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 present, the description compensates by describing the return shape (header with address, dates, payment terms, status code; positions with quantities, prices, values) and status code semantics. For a 10-parameter filter tool with fully documented schema, nothing material is missing.

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 baseline is 3; the description adds meaning by mapping its filter list onto the parameters and by explaining what the returned status code values mean for interpretation. Minor deduction because it does not itself clarify the limit/offset pagination caveat that lives only 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?

States a specific verb (Search) plus the exact resource (Collmex customer invoices and credit notes, record INVOICE_GET) and enumerates the filterable dimensions. This clearly separates it from siblings like collmex_list_open_items and collmex_list_sales_orders without needing to open any schema.

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?

The filter enumeration ('by invoice number, customer, invoice date range, customer order or product') plus 'Reads only; no PDF/XML export' gives a clear sense of when this tool applies and where its boundary lies. It does not explicitly name an alternative tool for document export, so it stops short of full when-not guidance.

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