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

Annotations already carry destructiveHint=true and idempotentHint=true, but the description adds crucial context: custom_<code> values are not immediately erased but clear on the next full product import; the addon requirement (without it returns 403 with addonCode+upsellUrl, and instructs to show the upsellUrl and not retry); and the exact return shape. This significantly enriches the behavioral profile beyond annotations.

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 compact and front-loaded: the primary action and purpose appear in the first sentence. Supporting notes (delay, addon, return) follow logically without redundancy. Every sentence adds value; no filler or repetition.

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 destructive, idempotent mutation with an optional parameter and a prerequisite addon, the description covers all necessary aspects: what is deleted, when it takes effect, how to re-import, optional parameter behavior, the error condition and required response, and the return contract (including both statuses and the applied field). No critical information 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 coverage is 0%, so the description must explain parameters. It does: code is the identifier ('by code'), apply is explained ('set apply:true to re-import now'), and project_id is noted as optional and inferred for single-project customers. All three parameters receive meaningful explanation, fully compensating for the schema gap.

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 the verb 'Remove' and the resource 'AI source (its CSV + registration)' and identifies the key 'code'. It clearly distinguishes this from delete_api_source or delete_feed by naming the resource type, so an agent can pick the correct deletion tool without opening the schema.

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 clarifies the effect ('so it is no longer applied on future imports') and the option to re-import with apply:true. It does not explicitly name alternatives or state when to prefer this over delete_api_source, but the resource type is unambiguous. Context is clear; exclusions are not stated.

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