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

Annotations already declare readOnlyHint=false, destructiveHint=false, and idempotentHint=true, so the description doesn't need to restate those. The description adds useful behavioral context by explaining the effect of each visibility value ('public' lets anyone with the link view; 'allowlist' restricts to verified people on the allowlist) and notes that 'allowlist' is Pro only. It does not mention side effects like whether existing share links are affected, but the annotations cover the safety profile and the description adds meaningful value beyond 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 compact and front-loaded: it opens with the user-intent trigger, then states the action, then explains the two enum values. Every sentence earns its place, and there is no redundant restating of the tool name or schema fields. The 'Pro only' note is a valuable constraint included without bloat.

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 two-required-parameter tool with full schema coverage and annotations covering safety and idempotency, the description is nearly complete. It explains the visibility values and the Pro restriction, which are the main non-obvious details. It does not describe the return value, but there is no output schema and the tool is a simple setter, so that is a minor gap. The workspace_id nuance is already fully documented in the schema.

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 adds value by explaining the semantic difference between 'public' and 'allowlist' in plain language, which goes beyond the schema's terse '`public` or `allowlist`' enum description. It also clarifies the user-intent mapping, which helps the agent select the right enum value. The workspace_id parameter is fully documented in the schema, so no additional description is needed.

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 ('Sets a site's visibility') and resource, and clearly distinguishes the two visibility values ('public' lets anyone with the link view; 'allowlist' restricts to verified people). It also opens with user-intent phrasing ('when the user says only certain people should see it, make it private, or open it to anyone with the link'), which makes the tool's purpose immediately recognizable. It is distinct from siblings like set_allowlist and set_collection_access because it focuses on the site-level visibility setting.

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 states when to use the tool: 'Use when the user says only certain people should see it, make it private, or open it to anyone with the link.' It also explains the meaning of each visibility value, which helps the agent choose between 'public' and 'allowlist'. It does not explicitly name alternative tools, but the when-to-use guidance is strong enough to route the agent correctly.

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