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

Annotations only declare readOnlyHint and openWorldHint, and the description adds substantial behavior beyond that: page size and ordering, captions only on page one, null authorHandle on collab reels, absent publish dates, the extra_fetch credit cost (1 credit per item, capped at page size), the grid fallback when the reels tab is unavailable, and that empty results aren't charged. raw.source is disclosed as the discriminator of which path answered.

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 purpose and pagination before edge cases; each sentence carries distinct information (ordering, pagination, null fields, extra_fetch, fallback, pricing). Slightly dense and runs long, but there is little 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?

No output schema exists, yet the description explains return shape (counts per reel, null text on later pages, null authorHandle for collabs, no publish date, raw.source), the fallback path, and cost model. An agent has enough to call it correctly and interpret the result.

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 high (83%), so baseline is 3, but the description adds real meaning: handle/user_id are alternatives ('Pass either'), cursor drives pagination, and extra_fetch carries a per-item credit cost with a page-size cap. cache_max_age remains undocumented in both, a minor gap.

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 ('Reels from a profile'), and immediately scopes it ('a profile's reels, newest first, twelve per page, each with like, comment and play counts'), which distinguishes it from siblings like instagram_reelsSearch, instagram_trendingReels and instagram_userPosts without opening any schema.

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?

Gives concrete usage context: pass either handle or user_id, follow pagination.cursor for older reels, and set extra_fetch=true when publish dates are needed. It stops short of naming which sibling to use instead for hashtag/audio/trending reels, so exclusions are only implied, not stated.

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