blockrun_exa

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

Annotations already cover the safety profile (readOnly, non-destructive, open-world), so the description is not obligated to restate those. It instead adds genuinely new behavior: all calls are POST with documented body shapes, every call incurs a base charge plus a flat transaction fee, the 402 response header carries the exact amount, and contents accepts up to 100 URLs per fee. That cost/billing disclosure is exactly the kind of context an agent cannot get from 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-loaded with the one-line purpose, then a scannable aligned table of paths and body shapes, then categories and a pointer to the skill. Dense but every line is load-bearing; only the parenthetical about reserving $0.002 is borderline padding.

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 dispatcher with no output schema, the definition supplies pricing, per-path bodies, category values, and a documented exclusion, and it routes to the exa-research skill for full request/response shapes. The reliance on an external skill for response formats is the main residual gap, but it is explicitly signposted rather than left silent.

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 would be 3, but the description goes well beyond the schema by specifying the body shape for each of the four paths (query/numResults/category/includeDomains/excludeDomains for search, urls for contents, etc.). It also enumerates the valid category values and the acceptable path names, which the schema only gestures at with 'e.g.'.

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 opening line names a specific verb and resource ('Neural web search via Exa') and characterizes it as semantic rather than keyword-based, which is meaningful. The four enumerated paths make the surface area concrete. It stops short of explicitly distinguishing itself from the sibling blockrun_search, so an agent must infer the difference from the 'neural' framing.

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' and the per-path cost table imply when to reach for this tool, and 'Exa does not serve X/Twitter content' gives one explicit exclusion. However, there is no statement of when to prefer it over blockrun_search or the other search-adjacent siblings, leaving the selection decision largely implicit.

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