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

Annotations only cover safety (readOnly, idempotent, non-destructive); the description goes well beyond by disclosing ordering ('mostly most recent first, though X can place some accounts out of that order'), a fixed page size of about 70, the absence of a limit parameter, 404/protected-account semantics, and a detailed billing model. This is exactly the behavioral context the annotations cannot carry.

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?

Front-loaded with the purpose, then ordering, pagination, errors, and cost in a sensible sequence with no filler. Minor redundancy: pagination via meta.nextCursor is stated early and restated in the closing sentence, and 'Billed per account returned' is partially repeated by the itemized credit formula.

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 carries the return-value burden and does explain ordering and the meta.nextCursor field plus the cost per returned profile, which is enough to drive a pagination loop. It does not describe the shape of each returned account object, which is the one remaining gap for a tool with no output schema.

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 baseline is 3 and the schema already documents both parameters including the 400 on a foreign cursor. The description adds genuine meaning: there is deliberately no limit parameter, and the account is resolved on the first page but carried inside the cursor on later pages, which explains why cursor cannot be reused across requests.

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 first sentence names a specific verb and resource and fixes the direction of the relationship ('the accounts an X account follows'), which reads as distinct from the get_x_user_followers sibling. It never names that sibling explicitly, so the agent must infer the contrast rather than being routed.

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?

Usage context is concrete: paginate whenever meta.nextCursor is set, pass it back as cursor, and expect a 404 for nonexistent or protected accounts. What is missing is selection guidance against alternatives (followers, search_x_users, get_x_users) for when an agent should choose this tool over them.

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