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

Goes well beyond the readOnly/idempotent annotations: it discloses the response shape ({options:[{value,label}], hasMore, nextOffset}), the pagination loop (offset from nextOffset while hasMore), and the important detail that the stored value is `value` not `label`. It also documents the project_id inference behavior and the project_id_required error path, which neither annotations nor schema reveal.

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?

Almost every sentence contributes new, actionable information and the purpose is front-loaded in the first clause. However, it is delivered as one dense run-on paragraph mixing purpose, return shape, usage paths, pagination and target resolution; breaking it into short sections would improve scanability without losing content.

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 5-parameter, no-output-schema read tool, nothing an agent needs is missing: it covers what the tool returns, how to page, how to identify the target, where ids come from, and what to do with the result. The empty-options edge case is also handled.

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 80%, so the schema already documents offset, feed_id, integration_id and attribute_code; the description largely restates the exactly-one-of constraint but adds the provenance of each id (list_feeds, list_marketplaces/list_ads, get_feed/get_marketplace_attributes/get_ad_attributes). It adds the most value on project_id, which has no schema description, by explaining inference and the list_projects fallback.

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?

States a specific verb and resource ("Get the allowed OPTION choices (value + label) of a target feed/channel attribute") and then defines the concept of a Set option attribute so the agent knows exactly which class of attribute is served. It also explicitly separates this from free-text attributes by pointing to set_value, making it easy to tell apart from the many sibling attribute tools.

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?

Gives explicit when-to-use ("Use this when an attribute accepts only listed values"), a negative case (empty options = not a closed-option attribute, use set_value instead), and two concrete downstream paths: constant mapping via map_feed_attribute / map_marketplace_attribute / map_ad_attribute, or a conditional rule with the setoption operation, referring to list_rule_transforms.

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