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

Annotations only declare readOnly/openWorld/non-destructive; the description goes well beyond them by disclosing per-call credit pricing, pagination via end_cursor on posts and reels, and the critical trap that highlights need the short pk while posts/reels need the long user_id. That is exactly the operational context an agent cannot get from the structured fields.

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-loads the resource then organizes everything as a scannable per-action list, so the length is justified by six actions. The repeated 'Inputs:' lines per action partially duplicate the schema descriptions, which is the only 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?

For a six-action tool with an output schema present, the description covers what each action returns, its inputs, its pricing and its pagination behavior. Nothing needed to invoke an action correctly is missing, and return-value detail is appropriately left to the 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 already 100%, so the baseline is 3, but the description adds real meaning: it explains the two-ID model (user_id vs pk), which action consumes which, that username returns more posts than user_id, and that highlight_id must come from action=highlights. It reinforces rather than merely restating the schema.

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 (Instagram profiles) and enumerates the six concrete operations with specific verbs (get details, resolve ID, list posts/reels/highlights, get highlight stories). An agent can distinguish this from siblings like instagram_post, instagram_reels and instagram_search because the description covers the whole profile surface plus highlight stories, which the siblings do not.

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 clear in-tool routing: 'For reels only, use action=reels', 'Use action=highlight_details to get the stories in one highlight', and per-action required/optional inputs. It does not, however, tell the agent when to pick this tool over the sibling instagram_post or instagram_reels tools, so sibling differentiation is left to inference.

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