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

Annotations already declare destructiveHint, idempotentHint, and openWorldHint, so the safety profile is partly covered. The description adds genuinely useful context: checkoutProvider changes affect checkout on the project's sites after publication, plus prerequisites for each provider. It doesn't state explicitly what 'destructive' means here (e.g., whether clearing a field removes it), leaving some gap.

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?

Three tight sentences, front-loaded with the core action, followed by the impactful side-effect/consequence and the publishing disambiguation. Every sentence carries weight and nothing is redundant.

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 mutation tool with no output schema, it covers the action, the notable side effect, and prerequisites. 'Update the supplied settings' adequately conveys partial-update semantics, and return values are not required without an output schema. It could add permission/authorization context, but overall it is complete enough to invoke correctly.

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 only 17%, so the description is expected to compensate. It names the settable fields and gives real semantics for checkoutProvider (shopify vs replo), which the bare enum lacks. However, it doesn't explain formats for currency (3-letter code) or timeZone, so compensation is only partial.

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 a specific verb (update) on a specific resource (Replo project) and enumerates the exact updatable fields (name, time zone, currency, support email, checkoutProvider). This clearly distinguishes it from create_project, get_project, and update_site/update_product.

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?

Clarifies when checkoutProvider can be changed (Shopify requires a connected store, Replo requires payments onboarding) and explicitly warns that 'Publishing is a separate action,' steering the agent away from using this for deployment. It doesn't name the alternative sibling (publish_site) directly, so it falls short of the 5 bar.

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