Exa Agent research run

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

With no annotations provided, the description carries the full burden and does well: it discloses async behavior, the default waitSeconds wait of 120, that a still-running call returns a run id for exa_agent_get, cost tiers per mode/effort, and a usage-based cap of $1/run. It does not cover auth/permissions or rate-limit behavior, so it is strong but not exhaustive.

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 front-loaded with purpose and exclusions, then packs cost and wait behavior into two dense but purposeful sentences. Every clause adds decision-relevant information for an agent; there is no 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?

Given a 14-parameter, no-annotation, no-output-schema tool, the description covers the essential operational picture: async execution, waiting, fallback run id, cost model, and sibling alternatives. It leaves detailed parameter semantics and output schema usage to the well-documented input schema, so it is complete enough for correct invocation, though a bit more on structured output behavior could help.

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 description coverage is 93%, so the baseline is 3, but the description adds real meaning beyond the schema by mapping mode and effort to cost/quality tiers ('fast = minimal ($0.012) · auto = low ($0.025) · max = ultra ... capped at $1/run') and by stating the waitSeconds default and run-id fallback. Minor parameters like inputData and outputSchema are left to the schema, which is acceptable given coverage.

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 and resource — async multi-step Exa Agent run for deep research — and enumerates concrete use cases like list-building, row enrichment, multi-hop research, and structured JSON with citations. It explicitly distinguishes itself from exa_search and exa_answer, so an agent can route correctly without inspecting schemas.

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?

It gives explicit when-to-use guidance via the deep research use cases and an explicit when-not-to-use clause: 'Not for simple lookups (use exa_search or exa_answer).' It also explains the wait/fallback path to exa_agent_get, covering alternatives and follow-up behavior.

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