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

With no annotations, the description carries the burden of behavioral disclosure. It reveals that restrictions are permanent from the caller's perspective, that only the owner can unlock them, and that an unlock is performed via a returned settings link. This goes beyond the input schema and meaningfully informs the agent of side effects and ownership constraints.

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 compact sentences deliver the action, the scope, the operation-key source, the wildcard option, and the irreversibility/ownership caveat. Every sentence adds information with no filler or redundant restatement of the tool name.

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 description is complete enough for a two-parameter mutation tool with an output schema. It explains how to specify operations, what scope the restriction applies to, and the critical limitation that restrictions cannot be removed. Given the output schema is present, not explaining the return value is acceptable.

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 0%, so the description compensates by explaining the operations parameter: valid values come from credential_operations and '*' is the wildcard for every operation. The credential_id parameter is only implied by 'this specific credential', but its meaning is largely inferable from the name and required context.

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 a precise verb and resource: 'Add approval restrictions to this specific credential.' It also scopes the action across 'all agents and MCP callers,' which clearly distinguishes this from read-only sibling tools like list_credential_requests or search_credentials.

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 gives concrete usage context: it tells the agent to use operation keys from credential_operations or '*' for all operations, and it notes the tool cannot remove restrictions. It does not explicitly name an alternative tool or a 'when not to use' condition, but the boundary and operation-key guidance are clear enough.

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