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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds no behavioral information such as pagination limits, filter constraints, or data availability restrictions. Those details appear only in the criteria parameter description, not in the tool description itself. Thus, the description contributes little beyond 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?

The description is extremely concise, a single sentence with no filler. However, it is under-specified to the point of being almost tautological, providing only a verb and resource. It is not verbose, but it also does not earn its place by adding any informative value beyond the name.

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?

The overall tool definition is rich because the criteria parameter description thoroughly covers operators, limitations, pagination, and excluded data. The description itself is minimal, but it does not need to repeat those details since the schema handles them. Still, the description lacks any note about the return format or relation to sibling tools, making it only marginally adequate for a complex search tool.

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%, with detailed descriptions for both the company and criteria parameters. The tool description itself adds no parameter information; it merely restates the tool's purpose. Since the schema already carries the full burden of parameter semantics, a baseline of 3 is appropriate.

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 names the verb 'Search' and the resource 'purchase records', making the purpose unambiguous. However, it does not differentiate itself from the many sibling search tools (e.g., search_bills, search_invoices) beyond the resource name, and it offers no unique identifier or distinguishing capability. Still, it is specific enough to be understood.

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 no guidance on when to use this tool versus alternatives. There is no mention of using get_purchase for single records, no filter strategies, and no exclusions. It is a single sentence that gives no context for selection among the many search_* siblings.

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