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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint=false and destructiveHint=false, so safety is covered structurally. The description still adds real value beyond them: it never re-runs the work (idempotency in practice), the run is free, `wait` caps at 120 s, and results may come back partial. It stops short of describing the result envelope, though an output schema exists, so a 3 reflects solid but not exhaustive added context.

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?

Front-loaded with the trigger condition, then exclusions, then cost, then the waiting behavior — a sensible priority order with no filler. Some sentences are telegraphic fragments ('Not for slicing a finished research: get_research'), which is efficient but slightly clipped for readability.

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 two-parameter polling tool with an output schema, everything an agent needs is present: when to call it, alternatives, price, idempotency, the blocking-vs-polling tradeoff, the 120 s ceiling, and expected latency for research. Return values need not be described because an output schema exists.

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 0%, so the description carries the full burden and largely meets it: `wait` is explained as a blocking wait in seconds with a 120 s cap, contrasted with the polling backoff used when it is absent. `run_id` is only implied (an id from a paid tool whose run is still in flight) rather than defined by form or origin, which is the remaining gap.

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 ('returns its status and, once completed or partial, the full result') and anchors the call to a concrete trigger: a run id returned by a paid tool that is still running. It also names the siblings it is not (get_research for finished research, get_usage for past charges), so the agent can separate it from them without opening a 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?

Explicit when-to-use ('when a paid tool returned a run id still running') plus two explicit when-not cases with the correct alternative named for each. It also gives a fallback policy when `wait` is omitted (poll at 2 s, doubling to 10 s) and warns that research takes minutes, so the agent knows how to behave in both modes.

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