Ask Heliyos

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

Annotations only say destructive, non-idempotent, non-read-only; the description goes well beyond by disclosing the approval gate for consequential actions, the 90 s wait ceiling, the minimum 120 s client timeout requirement, credit consumption, and the dual-run consequence of repeated calls. These are the operational facts an agent cannot infer from the annotations and would otherwise trip over.

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 purpose and examples, then moves efficiently through safety, timing, follow-up, and cost. Minor waste: it restates the return payload both inline ({run_id, status, thread_id}) and again at the end as structuredContent, which is redundant given an output schema exists.

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 complex, long-running, destructive orchestration tool this covers everything an agent needs before calling: scope of side effects, approval semantics, latency and timeout, follow-up path, conversation continuity, and cost model. Return values are additionally spelled out even though an output schema is present.

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% and both parameters are already documented in the schema, so the baseline is 3. The description's note about passing thread_id to continue the same conversation largely restates the schema field description and adds nothing about the 20,000-character message limit or content expectations.

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?

States a specific verb and resource ('Asks Heliyos (the orchestrator and its workers) a question or gives it a job, in plain language') and backs it with two concrete examples that show the level of abstraction expected. It is clearly distinguishable from the granular siblings like heliyos_records_update or heliyos_tasks_create because it is the natural-language entry point.

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?

Explicitly routes the agent: use this for plain-language jobs, call heliyos_runs_get with wait: true when the result is 'Still running', and pass thread_id to continue a conversation. It also gives a pre-call instruction ('confirm jobs that change things with the user first') and warns that calling twice starts two runs, which is exactly the when/when-not guidance an agent needs.

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