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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds the useful polling/repeat-call semantics, but says nothing about session states, timeout, or what completion looks like.

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?

One sentence, zero waste, with the key dependency (start_connect) front and center. Nothing to trim.

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 polling tool with no output schema and an undocumented required parameter, the description is thin: an agent cannot tell what the response contains or how to judge when polling is finished. It is minimally viable but leaves a real gap for its tool type.

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 exactly 50%: profileId is documented in the schema, connectionSessionId is not. The description only implicitly tells the agent the session ID comes from start_connect; it adds no format or sourcing detail beyond that, so baseline 3 is right.

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 (poll) and resource (connection session) and ties it to the sibling that creates it, start_connect. An agent can distinguish this from start_connect and other read tools, though it doesn't say what the polled session represents.

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?

"Poll" plus "started by start_connect" gives clear context: call this repeatedly after start_connect until the session resolves. It stops short of saying when to stop polling or what states to expect, and names no alternative, 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.