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

Annotations cover the operation profile (readOnlyHint=false, openWorldHint=true, idempotentHint=false), and the description adds substantial beyond them: the paid Bright Data collection trigger, the seven-day cache write, force_refresh's cost implication, pending-job resumption, sample-sorting caveats, the no-cookie sampling method, and the heuristic-authenticity caveat. 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?

Front-loads verb, scope, and runtime before the routing and cost details. Every clause is load-bearing: cost, cache, latency, resumption, and the heuristic caveat each change how an agent should call or interpret the tool.

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?

With no output schema, the description should hint at what comes back. It discloses sample ordering and the authenticity caveat, which is good, but never says what the analysis output contains (themes, sentiment, counts). Otherwise the operational picture is complete.

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 100%, so the baseline is 3. The description still adds operational meaning for force_refresh beyond the schema wording — that a later explicit call without it resumes a pending job with no new scrape — which is genuinely useful decision context for the caller.

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 + resource + scope ('Analyzes up to 100 recent reviews') with a latency envelope, and explicitly distinguishes itself from siblings check_product_trust and compare_products. An agent can route to it without opening 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?

Gives an explicit gating condition ('Use only when Amazon review-sample analysis is explicitly requested') plus named alternatives and what each alternative is for (trust score vs. ranking). When-to-use and when-not-to-use are both covered.

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