Произвольный GraphQL-запрос

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

The description goes far beyond the annotations. It explains why destructiveHint is set (documents may be mutations), warns that HTTP 200 does not mean success for mutations (userErrors must be checked), discloses that mutations are not retried to avoid double application, that THROTTLED is auto-retried, and that the cost is returned in the response with a 1000-point limit. These are critical behaviors not visible in annotations or schema.

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 dense but each sentence earns its place. It front-loads the core purpose and usage, then flows logically through the destructive annotation, userErrors caveat, retry semantics, and cost limits. No redundant or vague 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 complex, open-world GraphQL tool with no output schema, the description provides all essential context: purpose, auth (token/shop/API version inserted by server), error interpretation (userErrors), retries, and cost. An agent has enough to call it correctly and know what to inspect in the response.

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 100%, so the schema already documents all three parameters. The description restates that variables are passed via 'variables' and implies queries are safe, but adds no substantive meaning beyond the schema's property descriptions. Baseline 3 is appropriate.

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 action (executes an arbitrary GraphQL document against the Admin API) and explicitly clarifies it's the catch-all for operations lacking a dedicated tool, listing examples. This distinguishes it from the sibling tools (e.g., get_product, create_product) without opening any 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?

Explicitly says to use this tool for everything that does not have a separate tool, providing examples like metafields, media, collections. This is a clear when-to-use instruction and implies using dedicated siblings when they exist. It also adds operational cautions about mutation vs query and retry behavior.

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