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

The description adds significant side-effect context beyond the destructiveHint annotation: removal applies to every product, is immediate only when apply is true, otherwise clears on next import, and is guarded by an addon requirement with exact error fields. It also states the return shape, so the agent knows what success looks like.

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?

Two sentences front-load the primary action and then pack optional behavior, addon error handling, and response format without redundancy. Every clause adds operational value.

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?

The description covers parameters, behavior, error handling, and return shape, which is strong given there is no output schema. It leaves a small ambiguity around whether project_id is required for multi-project customers and does not state behavior when code is absent, so it is not fully complete.

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%, yet the description explains all three parameters: code (the attribute identifier), apply (controls immediate versus next-import clearing), and project_id (optional, inferred for single-project customers). This fully compensates for the schema's lack of parameter descriptions.

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 'Remove an API source attribute by `code` from every product so it is no longer applied', naming the verb, resource, and scope. This clearly distinguishes it from set_api_source (set vs remove), list_api_sources (list vs delete), and delete_ai_source (API vs AI).

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 tells the agent when to set apply:true (re-import now) versus letting it clear on the next import, and when to stop by showing the upsellUrl and not retrying on addon_required. project_id inference is also covered, but the description never names sibling alternatives or an explicit do-not-use condition, so it stops short of a 5.

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