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

Annotations already cover read-only and non-destructive semantics, yet the description adds genuinely useful behavior: which fields each follower returns, cursor pagination, and a cost/purchase warning ('Repeated requests may purchase data again'). The credit information is self-contradictory ('at least 10 Nexscope credits' versus '1 credit per request'), which muddies an otherwise valuable disclosure.

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?

The core is fine and front-loaded, but the text is padded with pasted vendor boilerplate ('GitHub Followers API View Pricing Get public followers...', 'Examples are not guaranteed prices') and repeats the identifier instruction twice. The duplicated and conflicting credit statements force the reader to reconcile noise.

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, listing the follower fields is a real contribution, and pagination plus cost awareness round it out. However, the conflicting credit figures and the absence of guidance for the all-optional parameter set leave ambiguity an agent must resolve by guessing.

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 three parameters are already documented; the description only restates that username, handle, or URL may be passed. It adds no new detail on cursor semantics or precedence when multiple identifiers are given, so it sits at the baseline.

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 opening sentence gives a specific verb and resource ('Retrieves public GitHub followers for a user'), and the name makes the followers-vs-following split from social_github_user_following obvious. It does not explicitly name that sibling or other GitHub user tools, so differentiation is implicit 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?

It tells the agent which identifier forms are acceptable (username, handle, or full user URL) and that cursor pagination is supported, which is useful invocation guidance. It never says when to choose this tool over the sibling GitHub user tools, nor what happens if no identifier is supplied despite all parameters being optional.

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