instagram_search_recall

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint false. The description adds valuable behavioral context beyond that: channels fail independently so rate limits on one do not lose others, and the tool is intentionally low-precision-per-probe. It also explains return characteristics like 'corroborated' counts. No contradiction with annotations.

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 moderately long but each section earns its place: opening purpose, channel list, strategy, repeatability, and then args/returns. The main action is front-loaded, and the list is compactly formatted. Slightly verbose but not wasteful.

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?

Given the complexity (2 params, nested object, many channels, and an output schema exists), the description covers channel options, probe strategy, error independence, repeatability, and return fields. It does not detail the exact probe argument format beyond the schema example, but the schema covers that. The existence of an output schema reduces the burden on the description for return values.

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% (both parameters have descriptions), so baseline is 3. The description adds meaning beyond the schema by explaining each channel type (e.g., 'places (authors of geotagged posts - the strongest location probe)') and the overall probe structure, which enriches understanding of how to use the `probes` 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 states a specific verb ('sweep') and resource ('Instagram for candidates') and clearly explains the action of adding them to a search pool. It enumerates all channels, distinguishing it from the many sibling search tools by describing its multi-channel aggregation role.

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?

Provides clear strategic guidance: 'Fire many cheap probes rather than one careful one' and explains why (precision per probe is poor by design, corroboration across channels matters). It also states it is repeatable to widen the pool and that channels fail independently, giving context for when to use this tool. It does not explicitly name alternative tools, but the guidance is strong enough.

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