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

The annotations declare readOnlyHint=false on what looks like a pure lookup, and the description resolves that apparent oddity by stating results are 'Saved in the user's Puley history' — a genuine side effect the agent could not infer from the annotation alone. It also discloses the 10-creator cap and that it reaches external platforms (matching openWorldHint=true). It stops short of noting idempotency behaviour or what happens on invalid handles.

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?

It is short and the batch limit is front-loaded, but it is written as a run-on fragment with no clear sentence boundaries, and the metric list ('typical as a share of followers') is compressed to the point of ambiguity. Information density is high, yet the phrasing costs readability.

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 only two parameters, no output schema, and annotations covering the safety profile, the essential information is present: inputs, the metrics returned, the batch cap, and the persistence side effect. Missing pieces — return format, behaviour beyond the 10-creator limit, error handling — are minor for a tool this simple.

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 description coverage is 0%, so the description carries the full burden and largely does: 'creators' is defined as comma-separated usernames, and 'platform' is constrained to instagram, tiktok or youtube — a constraint the schema does not encode as an enum. It omits accepted handle formats (with or without '@', URLs) and case sensitivity, leaving a small gap.

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 names the resource (creators) and enumerates the exact payload returned: followers, typical views/likes on recent posts, typicals as a share of followers, engagement, and recent breakout posts. That is far more than the vague verb 'check' conveys on its own. It does not differentiate itself from near neighbours such as viral_outliers, comment_insights, or find_channels, so it falls short of a 5.

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?

'Up to 10 creators side by side before paying them' implies a vetting/decision-support use case and states a hard batch limit of 10. However, it never says when to prefer this over viral_outliers or find_channels, nor what to do when more than 10 creators must be evaluated. Usage is implied rather than prescribed.

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