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

Annotations already declare readOnlyHint and openWorldHint=false, so the description is not carrying the safety burden. It does add genuinely non-obvious context beyond the annotations: that no API key is required and that the two ids come from the start response. It stops short of saying what a poll returns or whether an incomplete result is possible.

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 short sentences, front-loaded with the action, then the inputs, then the auth note. Every sentence carries distinct information and nothing is padded.

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?

There is no output schema, so the description should indicate what a poll returns (status field, completion indicator, partial results). It says only "poll results," leaving the return shape and polling-termination semantics to inference — a meaningful gap for a polling tool.

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% — both scanId and guestSessionId are documented in the schema, including that they come from guest_start_scan. The description repeats that provenance but adds no new detail such as format, lifetime, or whether guestSessionId is optional in practice.

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 and resource ("Poll results") and ties it directly to guest_start_scan, so the agent understands this is the retrieval counterpart to the start tool. It is not an explicit contrast with siblings (discover_tools is unmentioned), but the start/get pairing is clear enough to route correctly.

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 results for a guest_start_scan" implies the tool is called after starting a scan and may be called repeatedly, but there is no explicit guidance on retry cadence, when to stop polling, or what to do if results are not yet ready. Usage is implied rather than stated.

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