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

Annotations only declare the generic profile (non-readonly, open-world, non-idempotent, non-destructive), while the description adds substantial behavior: duplicates are skipped, exact words are preserved, no token is needed for the primary sources, there is a monthly per-account allowance, each call runs ~40 seconds and returns a job_id plus progress, and the apify_token is never stored and is billed to the user. This is exactly the extra context annotations cannot carry.

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?

The core behavior is front-loaded in the first sentence, followed by source coverage, the async job flow, and the preview recommendation. It is dense with parentheticals and slightly run-on, but nearly every clause carries operational information rather than filler.

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 13-parameter, zero-required tool with no output schema, the description covers the calling workflow (preview then job_id loop), the progress/status return format, and the allowance/alternative-source behavior. What is not covered is minor (exact response fields, full source-by-source matrix), and annotations carry the safety profile, so an agent has enough to invoke it correctly.

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 69%, and the description adds real meaning beyond it: the job_id continuation/stop loop, what preview=true returns (source, total, sample) and that it imports nothing, the semantics of apify_token and its persistence across job_id calls, and low_rating_status overriding status for 1-3 star reviews. It leaves method, countries, min_rating, copy_images, and max_reviews to the schema, but adds clear value on the non-obvious parameters.

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?

The description states a specific verb+resource (fetch/import reviews from a public review page into a space) and enumerates the exact sources supported, distinguishing it from the generic sibling import_testimonials. An agent knows immediately what this tool does and its scope.

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?

It gives concrete workflow guidance: run preview=true first, pass apify_token only for the listed second-tier sources or when the allowance is exhausted, and expect use_another_route with an alternative (Claude's own fetch). It does not explicitly contrast against the sibling import_testimonials, so it falls just short of a full when/when-not/alternatives statement.

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