search_relations

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

With no annotations provided, the description carries the full burden of disclosing behavior. It states the pagination behavior ('up to 100 contacts per page'), the return fields ('IDs, codes, names, and contact details'), and the special case for empty searchValue. While it does not explicitly say 'read-only', the verb 'search' and 'Returns' imply a safe operation. This is sufficient for a search tool, though an explicit read-only note would improve clarity.

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?

The description is two sentences, front-loaded with the main purpose. Every sentence adds value: the first defines the tool's function, and the second covers pagination and the all-contacts behavior. There is no fluff or redundancy (the empty-searchValue note is arguably duplicated in the schema, but it is a key usage point). Perfectly concise.

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 no output schema, the description adequately covers return values and pagination, which are essential for using the pageNumber parameter. It also highlights the behavior when searchValue is omitted. It does not mention the searchOption enum values or the domainId default, but those are already in the schema. The description is complete enough for a search tool, though it could mention that it is read-only to fully round out the context.

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?

The input schema provides descriptions for all 5 parameters (100% coverage), so the description need not compensate. The description adds little beyond the schema: it summarizes the search fields and repeats the empty-searchValue behavior already documented in the schema. The output note about return fields is not parameter semantics. Thus, the description does not significantly enhance parameter understanding beyond 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?

The description clearly states the tool's function: 'Search for Yuki relations (customers/suppliers) by name, code, VAT number, or other fields.' It specifies the resource (relations) and the action (search), with a clear scope of usable fields. It distinguishes itself from sibling tools like get_gl_accounts or process_invoices, which target different entities or operations.

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 description provides clear context: it is a search tool for relations, with a specific usage hint: 'Omit searchValue (or pass an empty string) to retrieve all contacts.' This implies when to use the tool, but it does not explicitly mention alternatives or when-not-to-use. Sibling tools are mostly for other data types, so the context is clear enough for an agent to select it appropriately.

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