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

Annotations already declare non-read-only, non-destructive, non-idempotent, closed-world, and the description adds real value beyond them: it says a notification is created, that nothing is granted, that an administrator must approve, and what is returned (request id plus pending status). The one gap is that it never warns that repeated calls create duplicate notifications, despite idempotentHint=false.

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?

Two dense sentences with the core action first, then the critical non-grant caveat and return shape. Nothing is redundant and no sentence could be removed without losing an important constraint.

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 mutation tool with no output schema and no annotation detail, the description covers the essential facts an agent needs: approval flow, side effect (notification), that no access is granted, and the return values. The unexplained result_offset parameter is the main remaining hole, and it is minor for the primary use case.

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 0% schema description coverage the description must carry parameter meaning, and it does partly: it clarifies that 'reference' is a vault URI (with an example) and that 'purpose' and 'reason' are stated justifications, while project_id is implied by 'to a project'. The fifth parameter, result_offset, is never mentioned and its role in a request-creating call is opaque.

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?

States a specific verb and resource: 'Ask an administrator to attach an existing vault reference ... to a project', with a concrete example value (vault://brevo/key). This is clearly distinct from sibling tools like request_access, use_secret, and export_secret, since it explicitly says nothing is granted.

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?

Gives clear context for when to reach for this tool and draws the boundary with downstream use/export ('using or exporting the reference needs a separate permission'), which implicitly points at use_secret/export_secret. It does not explicitly name alternatives or state when-not-to-use versus request_access, so it falls short of a 5.

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