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

Annotations declare readOnlyHint=false and openWorldHint=true but explain nothing about why; the description fills that gap with a concrete cost model (1 credit per creator lacking a report from the last 30 days, free otherwise). It also discloses the freshness fallback indirectly via the built-from-report framing. It does not state latency or behaviour when some creators lack reports and allow_outdated is false.

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?

Two short blocks, with the core capability and the comparison dimensions front-loaded before the cost note. Every sentence carries weight, though the cost instruction reads as an imperative aside rather than integrated usage guidance.

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 usefully enumerates the returned comparison dimensions, and the cost model covers the practical risk of invoking it. For a 4-parameter, non-destructive analytical tool, an agent has enough to call it correctly and to warn the user about charges.

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 75%, so the schema already documents market, platform and allow_outdated. The description adds no per-parameter meaning, and allow_outdated - the most ambiguous parameter - is never addressed in the prose. Baseline 3 is appropriate.

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 ('Side-by-side comparison of 2-5 creators') and enumerates the compared dimensions (size, growth, engagement, audience quality, geography), which clearly separates it from single-creator tools like get_influencer_report. It stops short of naming any sibling explicitly, so differentiation is inferred rather than stated.

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?

There is a procedural guideline ('Tell the user the cost before calling') but no guidance on when this tool is preferred over get_influencer_report or audience_overlap, nor any exclusions. Usage is implied by the description rather than spelled out.

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