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

Discloses the cost model (free first daily checks, then 5 credits each), the no-charge case for thin-data creators, 7-day free reuse, and the crucial caveat that this is a rule-based estimate rather than platform data with a presentation instruction. This adds substantial context beyond the annotations and explains why readOnlyHint=false while idempotentHint=true.

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 sentences, front-loaded with the core action, then constraints, pricing, and the estimation caveat. Every clause carries actionable information with no 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 no-output-schema tool it covers inputs, cost, reuse, and the nature of the result well. It stops short of describing the shape of the returned estimate (score scale, per-creator breakdown), which is the only remaining gap.

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 67%; the description compensates by explaining the provenance requirement for creator_ids and the meaning of search_id (the search these creators came from). It reinforces the 20-item cap already in the schema rather than adding new detail there.

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: 'Estimate how real up to 20 creators' followers are.' It even names the signals used (views, engagement, likes, following) and the 20-item scope, so an agent distinguishes it from search_creators or lookup_creators without opening a 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 explicit prerequisites (creator ids must come from this user's searches, lookups, or saved creators) and routes credit questions to get_account. It also states the when-not condition via the 7-day reuse rule and the fresh=true override, leaving little to inference.

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