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

Annotations only declare readOnly/openWorld; the description adds substantive behavior beyond them — result ordering (oldest first), payload contents (media URLs), and a cost signal ('Costs 1 credit'). It stops short of pagination/limit behavior for long-lived highlights or any auth/quota caveats.

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?

Three short sentences, each carrying a distinct fact (what it returns, id provenance, cost), with the core output description front-loaded. Zero filler.

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 usefully characterizes the return (stories with media URLs, chronological) and gives id provenance and cost. Only gap is result-set size/pagination behavior for large highlights, which matters for a list-returning tool.

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 50% and the required `id` is already well documented in the schema (highlight: prefix, bare number, or URL). The description restates the same accepted formats, adding little, and says nothing about `cache_max_age`, which is 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 a specific resource and scope: 'Every story in one highlight reel, oldest first, with its media URLs.' An agent can immediately distinguish this from instagram_userHighlights (which lists highlights) without opening the 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?

Explicitly routes the agent: the `id` comes from /v1/instagram/user-highlights, establishing the required call chain before this tool. No when-not guidance or mention of alternative ways to reach story content, but the prerequisite context is clear.

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