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

Beyond the annotations (readOnlyHint: true, destructiveHint: false), the description adds critical behavioral context: it reveals that the returned URL is a bearer capability and must only be revealed or opened when the user requests that action. It also flags the prerequisite of calling auth_verify for multi-space accounts. These go beyond the structured annotations and significantly aid safe usage.

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 two short paragraphs, front-loading the core purpose and then providing the endpoint and usage guidance. It is concise and every sentence carries necessary information. The only minor redundancy is the GET line, but it's useful for debugging. Overall, it is well-structured and not verbose.

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?

The tool has no output schema, and the description only states that it returns 'metadata' without specifying the fields or structure of the result. An agent would need to know what an embed link metadata object looks like (e.g., id, type, typeId, URL) to process the response. Given that the description covers usage and security but not the return format, this is a notable gap. It is otherwise complete for a read-only listing tool.

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 input schema already describes all three parameters with 100% coverage, including targetSpaceId's instruction to call auth_verify first. The description only reinforces this by repeating the targetSpaceId usage in prose, without adding new semantics. Per the rubric, high schema coverage yields a baseline of 3, and no additional meaning is introduced.

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 opens with 'List embed links the caller can manage' and clarifies it returns 'metadata without capability secrets.' This is a specific verb+resource statement that clearly distinguishes from the sibling tools embed_links_create and embed_links_revoke, which have obvious different actions. The GET endpoint further specifies the operation.

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 explicit guidance for multi-space accounts: call auth_verify, ask the user which space, and pass targetSpaceId. It also states when to create an embed link ('only when the user explicitly asks to share or preview that node'), which implicitly contrasts with listing. While it does not name alternatives directly, the context is sufficient for an agent to infer when to use this tool.

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