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

The annotations only declare readOnlyHint=false, openWorldHint=true, idempotentHint=false and destructiveHint=false. The description goes well beyond them: it discloses the background-job/asynchronous model, the immediate id return, the multi-minute latency, the credit cost scaling with depth, the account-level enablement requirement, and the need for an API key. That is exactly the behavioural context an agent needs before firing a long-running job.

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 outcome and the async contract, then grouped by parameter and prerequisite in short scannable sentences. Slightly redundant at the tail, where 'Needs research to be turned on for the account' and 'Needs a free SnoopScan key' state two overlapping setup requirements in separate trailing lines.

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 five-parameter, long-running, open-world tool this covers job lifecycle, expected latency, cost, prerequisites, and the status-check path. An output schema exists, yet the description still sets expectations for the report format (Markdown with numbered citations), which is a bonus rather than a necessity.

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 burden and largely meets it: `depth` is given four concrete values with page budgets (12/35/90/220) plus the cost trade-off, `provider` is given three concrete values plus the default rule, and `plan` is explained as an optional step list. However the `context` parameter is never mentioned anywhere in the description or schema, leaving one of five parameters opaque.

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?

Opens with a specific verb and resource ('Research a question on the web and get a report with numbered citations') and immediately distinguishes the tool from its sibling by naming `researchStatus` as the follow-up call. An agent can tell this apart from `search`, `crawl` or `extract` without reading 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?

Explicitly states the async contract: the call returns a job id at once, the work takes minutes, and progress is read via `researchStatus`. It also states the prerequisite ('Needs research to be turned on for the account') and that deeper runs cost more credits. It stops short of contrasting this tool with cheaper siblings like `search` or `extract` for simpler lookups, so there is no explicit when-not-to-use guidance.

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