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

Annotations already cover the read-only, non-destructive, closed-world profile, so the bar is lowered, and the description still adds real context: the filtered official Apify Store export as data source, snapshot semantics via data_updated/evidence, the specific rate types returned, and the important caveats that unknown and excluded IDs are indistinguishable and that listed rates are not total cost. Minor remaining gaps: no mention of pagination, caching, or latency.

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?

Four compact sentences with no filler, and the core question is front-loaded before the caveats. The final two clauses are dense and slightly telegraphic, but each sentence carries distinct information (source, returned metrics, limitations).

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 and only one input parameter, the description does the necessary work: it identifies the data source, names the returned fields (data_updated, evidence) and metric families, and flags interpretation limits (no winner across targets, rates not total cost). An agent has enough to call it correctly and interpret results.

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 0% on the single actor_ids parameter, so the description must carry the burden; it does usefully restate the 2-5 count and stresses that IDs must be 'exact'. It does not, however, explain the expected ID format (e.g., username/actor-name slug) or what happens with duplicate or case-variant IDs. Partial compensation only.

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: comparing two to five exact actor IDs, and names the metrics reported (usage, eligible run completion, compatible result-event rates). It is distinguishable from sibling comparators like compare_proxy_providers and compare_rag_extractors by its subject, though it never explicitly names them. The opening interrogative form is slightly indirect but the substance is clear.

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?

The 'two to five exact actor IDs' constraint and the caveat that unknown/excluded IDs are indistinguishable imply that callers must supply IDs they already trust, nudging toward find_scrapers first. However, no sibling comparison tool is named and no explicit when-to-use/when-not-to-use routing is given. Usage is inferable but not stated.

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