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

Adds real context beyond the annotations: 'no auth required', the return of mcp_key exactly once (which explains the non-idempotent profile declared by idempotentHint=false), and the cursor_mcp_json artifact the caller must write. It stops short of describing what happens on a call after already_delivered (error vs. status payload), which is the one behavioral edge left implicit.

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?

Three tight sentences, front-loaded with the purpose, then the payoff, then the operational cadence. No filler and nothing repeated from the schema.

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?

With no output schema present, the description compensates by naming the returned fields (mcp_key, cursor_mcp_json) and the terminal status values. Combined with the polling instructions and auth note, an agent has everything needed to invoke and loop this tool correctly.

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 100%, so both parameters are already documented by the schema; baseline 3 applies. The description reinforces setup_id's provenance ('from request_signup') but adds no syntax or semantics for the optional client enum beyond what the schema states.

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?

Names a specific verb (poll/check) and resource (request_signup session), and ties itself explicitly to the request_signup sibling that produces the setup_id. An agent can distinguish it from create_mcp_key or list_mcp_keys without opening any schema.

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?

Specifies the polling cadence (every 3 seconds) and the exact termination conditions (ready, expired, already_delivered), which is precisely the when-to-call/when-to-stop guidance an agent needs. The prerequisite (setup_id from request_signup) is stated inline, removing ambiguity about ordering.

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