Exa Agent runs: list, events, cancel, delete

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

With no annotations at all, the description carries the full behavioral burden and delivers almost none of it: it never says that delete is permanent or cancel is irreversible, whether either is idempotent, what permissions or key scope is needed, or what happens to a run's events after deletion. 'Remove a run' is the only hint of destructiveness, and it is euphemistic rather than explicit.

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?

One sentence, no filler, each clause maps to exactly one action — structurally clean and easy to scan. The terseness borders on under-specification rather than verbosity, so the compactness is only mildly a virtue.

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?

A four-mode tool with two destructive operations, no annotations, no output schema, and 25% schema coverage needs far more than one line. Nothing is said about return shapes, pagination, error conditions, or irreversibility, leaving significant gaps for anything beyond the happy path.

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 only 25% — the id parameter is documented in the schema, but limit and cursor have bare types with no description in either place. The description does not compensate: it says list returns 'recent runs on every key' but never explains what limit does, how cursor pagination works, or whether cursor/limit are ignored by events/cancel/delete.

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?

Uses a compact glossary form to bind each of the four enum actions to a specific behavior ('cancel = stop a running run', 'delete = remove a run'), so the agent can tell what each branch of the tool does. It does not differentiate the tool from close siblings like exa_agent_get or exa_agent_run, which likely overlap on retrieving a single run.

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 action glossary implies which action does what, but there is no explicit when-to-use guidance, no statement of which action to prefer over exa_agent_get/exa_agent_run, and no preconditions (e.g. that events/cancel/delete require an id, or that list is account-wide). The agent must infer selection rules from a single line.

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