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

Annotations already indicate non-readOnly, non-destructive, and idempotent behavior. The description adds valuable behavioral details beyond annotations: omitted fields are left alone (partial update), it returns the updated site, and it refuses duplicate URLs with a specific error (site_exists). These are critical for correct invocation and are not present in the schema or annotations.

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 four short sentences, each carrying distinct information: the action and fields, the partial-update behavior, the return value, and a failure condition. It is front-loaded with the primary action and has no redundant phrasing or filler. Every sentence earns its place.

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 tool with four parameters (one required), no output schema, and annotations covering the safety profile, the description is complete. It explains the mutation behavior, the return value, and the error condition. An agent has everything it needs to correctly invoke the tool and interpret the result, without needing to infer missing details.

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?

With 100% schema description coverage, the schema already documents each parameter's format and optionality. The description adds the crucial semantic that omitted fields remain unchanged, which is not inferable from the schema alone. It also reinforces that 'url' is one of the changeable fields. This adds meaningful value beyond the structured schema.

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 ('Change') with a specific resource ('a site') and enumerates the exact fields (url, timezone, week start). This clearly distinguishes it from sibling tools like update_funnel or update_goal, which target different resources. It also mentions the return value, making the intent unambiguous.

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 clear context by naming the exact fields that can be changed and the behavior of partial updates. It does not explicitly name alternative tools for creation or other updates, but the scope is evident from the tool name and sibling context. The condition about rejected duplicate URLs gives a specific when-not scenario, but there are no explicit exclusions for other use cases.

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