instagram_search_enrich

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint false. The description adds substantial non-redundant behavioral details: rate limiting risk, approximate API call counts, progress saving between candidates, lock release behavior, best-effort error handling, and idempotent re-entry. There is no contradiction with annotations. This far exceeds what annotations alone convey.

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 description is relatively long but every sentence adds value: purpose, cost, rate limiting, idempotency, error handling, and a returns summary. It is structured with a lead sentence and then explanatory details, followed by an Args section. While it could be tightened, the length is justified given the complexity of the tool's behavior and context. It is front-loaded with the purpose and then dives into important caveats.

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?

The description covers essential context: when to use (expensive stage, ranked subset), cost implications (API call counts, delay), failure handling (best-effort), idempotency (repeated calls progress), and even mentions the return fields. The presence of an output schema covers return structure, but the description also names the return keys. Parameters are fully documented in both schema and description. Nothing an agent needs to decide when and how to invoke this tool is missing.

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 each parameter has a clear description in the schema itself. The description's Args section largely repeats the schema information (e.g., 'include_about: Whether to read the account's country'). It adds minimal new meaning beyond the schema; it does mention that 'limit' relates to API calls and that 'posts_per_user' can be used for geographic placement, but these are already hinted in schema descriptions. Therefore, a baseline 3 is appropriate.

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 clearly states the core function: 'Fetch full profiles, posts and country for the most promising candidates.' It identifies the resource (candidate profiles) and the action (fetch) with a specific scope (most promising). It does not explicitly name sibling tools or contrast with them, but it positions itself as the enrichment stage in a search pipeline, which distinguishes it from similar search tools like instagram_search_shortlist or instagram_search_expand. The 'expensive stage' framing adds clarity.

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?

The description provides strong usage context: it is the expensive stage with rate-limiting risk, works on a ranked subset, makes multiple API calls per candidate, and is idempotent by skipping already-fetched items. It warns about deliberate delay and suggests calling repeatedly to walk further down the pool. It does not explicitly list alternatives, but it clearly explains when and how to use it within the search workflow. The 'best-effort' and 'progress saved' details also guide correct usage.

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