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

There are no annotations, so the description carries the burden. It implies read-only via 'Retrieve' and states what is returned (enterprise_connection summary including SAML or OIDC configuration). It also mentions the dependency on get_connected_accounts. However, it doesn't disclose error behavior, permission requirements, or potential side effects (e.g., nothing is mutated). This is adequate but not deeply transparent.

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 short paragraphs, each earning its place: purpose, prerequisite/usage, and return summary. The cost note is a single extra token. No filler or redundancy. Front-loaded with the primary action.

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 single-retrieval tool with an output schema present, the description covers the essential context: prerequisite step, instance targeting, and return contents. It doesn't discuss error cases or authorization, but given the tool's simplicity and output schema richness, it is sufficiently complete. Slight gap: no mention of how this differs from list_enterprise_connections, but that is a minor omission.

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 coverage is 100%, so baseline is 3. The description adds meaningful parameter behavior: 'Pass clerk_instance_id to target a specific connection, or omit it to use the default account.' This clarifies the optional parameter's role and default behavior beyond the schema description. The connection_id parameter is adequately covered by the schema, though the schema's generic note about 'update/delete/test' could confuse, but the tool's verb clarifies.

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 specific verb and resource: 'Retrieve a single enterprise SSO connection.' This clearly distinguishes it from list_enterprise_connections (which retrieves multiple) and other enterprise connection tools like create/update/delete. The scope ('from a connected Clerk application') is also explicit.

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 instructs to call clerk.get_connected_accounts first and explains how to target a specific instance (pass clerk_instance_id) versus using the default (omit it). This gives clear usage context. It doesn't explicitly name list_enterprise_connections as an alternative for multiple records, but the singular 'single' vs. plural sibling name makes it inferable.

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