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

With annotations already signaling readOnlyHint=false and idempotentHint=true, the description adds substantial behavioral context: the raw token is intentionally not returned over MCP, completing login does NOT authenticate the MCP session, status 'active' reports the GRANTED scope read back from the token, and the fallback credential behavior with scope differences between content and admin tools. No contradiction with annotations — it enriches them.

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 dense (~120 words) but every sentence carries distinct, high-value information: purpose, polling cadence, status semantics, auth caveat, fallback behavior, security disclosure, and lifecycle handling. There is no filler, redundancy, or restatement of the schema. The length is fully justified by the tool's behavioral complexity.

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 an output schema, so return values need no description-level coverage. The description covers all the remaining contextual needs: the orchestration relationship with create_auth_session, polling cadence, all three status outcomes (pending/active/expired) with appropriate actions, security constraints, and the critical downstream requirement to pass session_request_id on protected calls. Nothing an agent needs to invoke this correctly is missing.

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% and the schema description already says 'Must be passed exactly as received.' The tool description adds value beyond that by explaining where the ID comes from (create_auth_session), how it must be reused on every protected call, and what happens if omitted. This is genuine complementary information, not schema repetition.

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: "Polls a login session created by create_auth_session until the user completes the browser login." This clearly distinguishes the tool from its siblings (create_auth_session creates, this polls; authenticate is a different auth path) and states the terminal condition precisely.

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?

Explicit operational guidance is given: poll every 2-3 seconds while status is 'pending', start over with create_auth_session on 'expired', and pass session_request_id on every protected call afterwards. It also explains the consequence of omitting the parameter (fallback to the connector's bearer token) and which tool category that breaks (admin tools like pair_by_code). This is exemplary when-to-use-and-how guidance.

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