blockrun_exa

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

Annotations already mark this as readOnly, openWorld, and non-destructive, so the description only needs to add extra context. It adds useful behavioral detail: all calls are POST, each endpoint has specific pricing, contents is capped at 100 URLs, and search categories are listed. It does not cover errors or rate limits, but the annotation coverage lowers that burden.

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 the value proposition and then uses a compact, scannable bullet list for endpoints and body shapes. It is longer than a single-purpose tool description, but the multi-endpoint surface justifies the length; the 'documented in skill' note is slightly redundant with the inline shapes.

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 multi-endpoint tool with no output schema, it covers request bodies, path choices, categories, and pricing, and points to the exa-research skill for full response shapes and workflows. The main gap is that response semantics are deferred to an external skill rather than summarized inline.

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?

Even though every schema property has a description, the tool description adds substantial value beyond the schema by listing the four valid path values, the exact body shape for each, optional fields such as numResults and includeDomains, accepted categories, and pricing. An agent can construct a correct request without needing to open the external skill.

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 identifies Exa as the resource and names the core capability ('Neural web search... understands meaning'), then enumerates four concrete endpoint paths. It stops short of explicitly differentiating itself from sibling tools like blockrun_search beyond the 'not just keywords' hint.

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?

'Great for research' provides a clear context for when this tool is appropriate, and the endpoint/pricing breakdown helps an agent choose the right path. However, it does not explicitly state when to prefer blockrun_exa over sibling search tools or when not to use it.

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