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

Annotations only declare readOnly/non-destructive/non-open-world. The description adds real behavioral traits on top: no filtering, no sorting, stored order, one window at a time, cannot emit a file, and money values in minor units. These are exactly the operational facts an agent needs and are not derivable from annotations or schema.

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?

Front-loads the core purpose before pivoting to alternatives and limitations, and every sentence carries weight (import dependency, alternatives, limitations, file caveat, money units). It is dense and fairly long, but the length is justified by the tool's ambiguity risk; only marginal tightening is possible.

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?

Although there is no output schema, the description compensates by describing the return shape (flattened spreadsheet columns, ids included, minor-unit money) and the pagination behavior (one window at a time). For a 3-parameter read tool, all decision-relevant context is present.

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 schema already documents limit/offset/resource. The description still adds meaning: it clarifies the 'options' resource maps to product attributes, explains the id-bearing flat shape the update arrays key on, and frames limit/offset as windowing. It goes modestly beyond the baseline without restating syntax.

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 gives a concrete verb+resource ('Dump one resource in spreadsheet shape') and states the exact output shape (records flattened to import-compatible columns WITH id). It explicitly distinguishes itself from the read siblings (get_products/get_customers/etc.) that answer questions, so an agent can route correctly without opening schemas.

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?

It states the primary trigger ('export my catalogue / my customers'), the workflow prerequisite ('required first step before any import that changes existing records'), the correct alternative for questions, and the correct alternative for file downloads (Settings → Import / Export → Export). When-to-use, when-not, and alternatives are all explicit.

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