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

Annotations already cover read-only and open-world, but the description adds genuinely non-obvious traits: fixed page size of 30, a cost of 1 credit, and the warning that GitHub returns a reduced payload so per-account counts come back null. That last point prevents an agent from misreading empty fields as a failure.

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 short sentences, each carrying distinct information (identity, pagination, payload quirk, cost, input rule). The identifying clause comes first and nothing is repeated from the schema.

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?

Given no output schema, the definition of the return population, page size, and null-count caveat is enough to call and interpret results. Only the neither-identifier case and `cache_max_age` are left uncovered.

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 75%, so the baseline is 3, and the description earns a bump by stating the either/or relationship between `handle` and `url` — something the schema cannot express with both being individually optional. `cache_max_age` remains undocumented in both places.

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 the resource and the direction explicitly: 'Accounts following this user' — which separates it from the sibling github_following. The leading 'Followers' fragment is immediately disambiguated by the next clause.

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?

'Pass either `handle` or `url`' gives a usable calling constraint, and the 30-per-page note implies pagination. But it never says when to use this over github_user or github_following, nor what happens if neither identifier is supplied (0 required params).

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