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

Given the annotations (readOnlyHint=false, destructiveHint=false, idempotentHint=true), the description adds valuable behavioral context: it mentions that setting a new URL clears previous crawl state, which is a side effect not captured by the annotations. This is beyond what annotations provide. The description does not contradict annotations. A 4 is appropriate because it provides useful side-effect disclosure but could have been more explicit about potential side effects of clearing.

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 concise (3 sentences) and front-loads the core action (set or clear) and the primary detail (bare domains accepted). It includes relevant examples and follow-up instructions without extraneous fluff. Every sentence adds value.

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 simple setter tool with only 3 parameters and no output schema, the description provides all necessary context: what the tool does, how to use it, the side effect of clearing crawl state, and the need for refresh_website. The context parameter is about meta-analysis and is well documented in the schema. Nothing essential 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?

The schema description coverage is 67%, meaning two parameters (handle and context) have descriptions, but website does not. The description adds semantics for the website parameter: it mentions bare domains and the clearing behavior, which is helpful. However, since the schema covers most parameters, the baseline is 3, and the description adds moderate value beyond the 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 clearly states the tool's purpose: to set or clear the tenant's business website URL. It gives a specific verb and resource, and distinguishes it from refresh_website by explaining that setting a new URL clears crawl state and that refresh_website is needed afterwards. This differentiates it from the sibling tool.

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 explicitly explains when to use this tool (to set/clear the website) and provides a follow-up action: 'call refresh_website afterwards'. It also clarifies the clearing behavior with 'Pass website: "" to clear'. No exclusions are needed because the purpose is clear.

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