patch_subscription

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

With no annotations, the description carries responsibility for transparency. It reveals that the operation is a partial update (modifying only specified fields) and that it is disabled in read-only mode, indicating it is a write operation. However, it does not describe side effects, error conditions, idempotency, or permission requirements. The description is honest but not exhaustive.

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 extremely concise: two short sentences with no redundant information. It states the core action and the read-only restriction without fluff. This is ideal for an agent to quickly grasp the tool's purpose.

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 adequately covers the essential context for a partial update operation: it targets an existing subscription product and is a write action. However, it does not explain the significance of the update_mask parameter or the expected effect on the subscription resource beyond the schema field descriptions. Given that an output schema is present, return values need no explanation, but the description could add more context about the partial-update semantics.

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?

The schema already provides descriptions for all five parameters (product_id, update_mask, package_name, subscription, regions_version), achieving 100% coverage. The tool description adds no extra semantic meaning beyond what the schema states. Per the rubric, a baseline of 3 is appropriate when schema coverage is high and the description does not augment it.

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 clearly states the tool's function: 'Partially update an existing subscription product.' This is a specific verb+resource combination that distinguishes it from create_subscription, update_subscription (if exists), and other related tools. The term 'partial' implies a PATCH-like operation, which is clear enough for an agent.

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 provides minimal usage guidance, only stating 'Disabled in read-only mode.' It does not explicitly mention when to use this tool versus other update tools (e.g., update_subscription or batch_update_subscriptions), nor does it describe the intended scenario for partial updates. The read-only constraint is useful but insufficient for choosing among similar tools.

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