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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description is fully consistent with them. Beyond the annotations, the description discloses the exact return shape ({attributes:[{code, label, dataType}], returned, total}), the non-paginated single-call behavior (returned === total), the conditional taxonomy behavior depending on which id is passed, and the data-import prerequisite — all genuinely additive context.

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?

Seven sentences, each earning its place: purpose with examples, return shape, parameter differentiation, call ordering, optionality logic, prerequisite, and pagination. The most decision-critical fact (relationship to map_feed_attribute) is front-loaded in the first sentence, and there is no redundancy or filler.

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 the tool's complexity — conditional parameter behavior, a prerequisite dependency, a downstream caller relationship, no output schema, and 0% schema coverage — the description is remarkably complete. It covers return format, non-pagination, the neither-parameter case via the inference logic, and points to both get_import_status and list_projects for adjacent concerns. Nothing an agent needs to invoke it correctly is missing.

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 carries the full burden — and it delivers. It explains that feed_id adds the feed's taxonomy_* attributes for editor parity, that project_id alone omits taxonomy, and that project_id is optional but conditionally required (inferred for single-project customers, otherwise call list_projects). This semantic distinction between the two integer parameters is exactly what an agent needs to choose correctly.

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 ('List the source attributes the store provides') and immediately defines the tool's purpose: it enumerates the valid platform_code values for map_feed_attribute. Concrete examples (brand, ean, price, color, category_name) anchor the meaning, and the explicit link to map_feed_attribute distinguishes it from sibling attribute tools like get_ad_attributes or get_marketplace_attributes.

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?

Usage guidance is explicit and actionable: 'Call this BEFORE map_feed_attribute to choose a valid platform_code' states the ordering constraint directly. It also covers when to pass each parameter (feed_id for full parity with taxonomy_* attributes vs project_id alone), when project_id is inferred vs required, routes to list_projects as an alternative, and names the prerequisite get_import_status.

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