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

Annotations already mark the tool as readOnly, idempotent, and non-destructive, but the description adds meaningful behavioral context beyond that: it is aggregate-only by design, returns a single count, and explicitly excludes all personal data (PCD Level 2 deferred). This gives the agent important expectations about the response shape and privacy boundary, which annotations alone do not convey. No contradiction with annotations is present.

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 front-loaded with the core purpose and remains reasonably concise despite repeated emphasis on aggregate-only/no-PII across the main text and the routing line. The repetition of 'aggregate only — no PII' in both places is slightly redundant but does not obscure meaning. Overall, each sentence contributes to clarifying scope and use, so it is well-structured.

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?

For a simple read-only count tool with no output schema, the description sufficiently states that the return is a single number and that no PII is included. It covers the filtering capability via `query` and the required `companyId` through the schema. It doesn't specify the exact JSON response wrapper, but 'single number' is adequate for an agent to invoke the tool and interpret the result. Minor gap: no mention of error behavior or rate limits, but these are not critical for a low-complexity 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%: both `query` and `companyId` have clear descriptions. The description repeats the query syntax example and adds the context that the result is a single number, but it does not materially expand on parameter meaning beyond the schema. Per the baseline rule for high schema coverage, a 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 opens with a specific verb and resource: 'Get an AGGREGATE Shopify customer count only — a single number.' It explicitly distinguishes the tool from any customer-data-returning tool by stating it returns NO names, emails, or addresses, and it clarifies the aggregate-only design. This enables an agent to know exactly what the tool does and how it differs from siblings like get_top_customers or list_shopify_orders.

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 says 'Use when a person or agent needs how many customers exist, never who they are,' which provides clear when-to-use and when-not-to-use guidance. It also mentions the 'aggregate-only' nature and 'no PII' as a routing hint. However, it does not explicitly name alternatives (e.g., get_top_customers for details), so it stops short of the full 5 for alternative naming, but the context is unambiguous.

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