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

Annotations only declare readOnly/openWorld/non-destructive; the description adds substantive behavior an agent could not infer: results are cached for 24 hours when Instagram answers and retried sooner otherwise, permission failures surface as a 'reconnect' state, and sub-100-follower accounts return an explanatory `notes` field rather than zeros. It also states the data is available on every paid plan, which is real authorization context.

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 return payload is front-loaded in the first sentence and the constraints that follow are all load-bearing. It is dense and somewhat run-on, and the closing phrasing rules ('never call anything "link taps"') drift into output-style guidance rather than tool selection, but there is little pure waste.

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 must describe returns, and it does so field by field, plus edge cases (thin accounts, missing permission, caching window) and known limitations (no day-by-day split, no per-post follow counts). For a one-parameter read tool this leaves nothing material an agent would need before calling.

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% and the single parameter's description already explains omission behavior and the 5-account cap, so the schema carries the burden. The description adds nothing about `profile_ids` itself. Baseline 3 is appropriate when the schema fully documents the only parameter.

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 a concrete resource and enumerates exactly what it returns: followers by age, gender, top countries/cities, online hours, and follow/unfollow totals for 7 and 28 day windows. It also carves out boundaries against analytics-type siblings by stating 'These numbers describe followers, not everyone a post reached' and 'Instagram only: no other platform shares this', so an agent can separate it from get_analytics or get_engagement_summary without opening schemas.

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 gives clear contextual conditions for using the data: an account under 100 followers returns nothing and `notes` says so (report that, never zeros), and an account lacking insights permission returns 'reconnect'. It also warns against misattributing follows to posts. What it does not do is explicitly name the alternative tool to pick when the agent wants post-level reach or engagement instead.

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