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

Goes well beyond the annotations: the call blocks 30-60s, the deep pass runs in the background, DataForSEO credits are consumed, recent complete runs are reused with status 'fresh' and nextRunAllowedAt, and status 'processing' is returned if a run is in flight. These are exactly the operational facts an agent needs and none are in the structured fields.

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 action and its two execution modes, and every clause carries real information (timing, credits, caching, status values, next steps). It is somewhat dense with nested parentheticals, which slightly hurts readability but not substance.

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 non-idempotent action tool with no output schema, the description covers the async lifecycle, the status values returned, the credit cost, the caching/reuse rule, and the follow-up tools. Nothing an agent needs to invoke it correctly is missing.

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?

Only one parameter ('site') and the schema already documents it at 100% coverage, so the description does not need to add parameter detail. Baseline 3 applies since the schema carries the semantics and the description adds nothing further about the argument.

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 ('Starts keyword research for the site') and immediately explains the two-phase execution model (inline quick pass, background deep pass). It is trivially distinguishable from siblings like get_research_status, get_keywords, and list_research_runs.

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?

Gives explicit routing: poll with get_research_status, then read results with get_keywords. It also states when the call is unnecessary (a fresh deep run from the last 30 days is reused) and where the alternative lives (forced re-run only from the dashboard).

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