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

The description discloses critical behaviors beyond the annotations: it states sharing does not affect other access, explains that forwarding the email forwards access, and clarifies that re-sharing with the same address re-sends the existing link. It also notes the necessity of a Valet account. These details help the agent understand side effects and security implications, complementing the destructiveHint annotation.

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 three sentences, each serving a clear purpose: purpose, security behavior, and idempotency. It is front-loaded with the core action and wastes no words. The tone is direct and informative.

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?

Given 6 parameters, no output schema, and annotations that are complemented by the description, the description covers the tool's behavior comprehensively. It explains the security implications, idempotency, account requirement, and the effect of optional parameters. An agent can correctly decide to invoke this tool and understand the expected behavior.

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 coverage, the baseline is 3. The description adds context by explaining how parameters interact (e.g., access_ttl_seconds and expires_in_seconds compose, at most 10 emails). It also clarifies that sharing again with an existing address re-sends the link, which relates to the emails parameter. This adds value beyond the schema definitions.

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: 'Share a website with specific people by email.' It specifies that it works for private or password-protected sites and notes that sharing does not change who else can reach it. This distinguishes it from siblings like 'set_site_access' (which changes access) and 'publish_site', covering a unique action.

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 implies when to use (to email a link) and mentions the requirement to connect a Valet account. However, it does not explicitly contrast with alternatives like 'set_site_access' for programmatic access or 'publish_site' for making a site public. The context is clear but lacks explicit 'when not to use' guidance.

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