Update a product input

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

Annotations only state readOnlyHint=false (mutation), openWorldHint=true, idempotentHint=false, destructiveHint=false. The description adds substantial behavioral detail: update_mask semantics (comma-separated paths, omission applies all populated fields), the local rejection of masked paths without values (and pointing to raw_request for intentional erasure), the async refresh of the processed product, and the requirement that data_source match the source. These go beyond the annotations without contradicting them.

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 a single dense paragraph but logically front-loaded: purpose → key constraint → mask behavior → return → alternative. Every sentence carries necessary information, though it could be marginally tightened without loss. It avoids redundancy with the schema, so it earns a 4.

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 (mask semantics, async processing, alternatives for creation/clearing), the description covers all essential call-time aspects: how to specify fields, mask handling, data_source requirement, return value (updated ProductInput), and the async refresh. No output schema exists, but the return type is stated. 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 coverage is 100%, so the baseline is 3. The description adds meaning beyond the schema by explaining how update_mask interacts with request fields (must carry a value for each masked path, erasure behavior), clarifies that data_source must be the source holding the input, and gives a concrete example for product_attributes. This elevates it above a bare schema repeat, earning a 4.

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 states a specific verb ('Sparse-updates') and resource ('existing product input'), and immediately differentiates from siblings by calling it 'the cheap way to change price or availability without re-sending the whole product.' It explicitly names insert_product_input as the alternative for creation or wholesale replacement, so an agent can distinguish without opening other schemas.

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 gives explicit when-to-use ('cheap way to change price or availability'), a key prerequisite ('data_source must be the source holding the input'), and alternatives ('use insert_product_input' for create/replace, 'use raw_request' to intentionally clear attributes). No ambiguity remains about selection among siblings.

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