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

With no annotations, the description must carry the behavioral burden, and it does establish the essentials: GET implies a non-destructive read, and 'Explicit company required' flags a mandatory scoping/authorization input. It stops short of anything about error behavior (unknown purchaseId), missing-record handling, or whether the query parameter alters the read scope.

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 short fragments, front-loaded with the identity of the operation before the constraints. No filler sentences, though the terse API-route phrasing trades readability for compactness.

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?

An output schema exists, so return values need not be explained, but for a no-annotation tool the description leaves too much open: no statement of what a 'purchase' record is in this domain, no sibling differentiation, and the only guidance pointer (describe_nextesy_operation) does not help an agent decide to call this 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 0%, so the description must compensate, and it does partially: the path template explains purchaseId, 'Explicit company required' explains company_name, and 'Flat query fields' signals the query object's shape. What is missing is what fields the flat query accepts and whether query can expand or filter the response — a meaningful gap at three undocumented parameters.

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 endpoint template 'GET /api/v1/sales/purchases/{purchaseId}' does convey fetching a single purchase by ID, distinguishing it from 'list_purchases' by the path parameter. However, it is phrased as a raw API route rather than a stated purpose, and an agent must decode the HTTP verb and path to infer 'retrieve one purchase'.

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?

'Explicit company required' is a real prerequisite, but there is no guidance on when to use this versus list_purchases or get_purchase_payments, and no exclusions. The pointer to 'describe_nextesy_operation for filters' is a meta-tool reference, not an alternative for this operation, so it reads like template boilerplate rather than routing help.

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