Fetch a run's current status, summary, pending approvals, and (once settled) the agent's final reply.
| Name | Required | Description | Default |
|---|---|---|---|
| run_id | Yes | A run id (trun_...). |
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | ||
| object | Yes | ||
| result | No | ||
| reused | No | ||
| status | Yes | ||
| chat_id | No | ||
| summary | No | ||
| task_id | Yes | ||
| task_name | No | ||
| created_at | Yes | ||
| started_at | No | ||
| completed_at | No | ||
| error_message | No | ||
| credits_consumed | No | ||
| pending_approval_ids | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate read-only, idempotent, non-destructive. The description adds that it returns current status, summary, pending approvals, and final reply once settled, which is useful context about the return content. No mention of rate limits or auth, but not required given the simple nature.
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 concise sentence, no fluff, well-structured.
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?
Covers the purpose, what data is fetched, and the nuance about 'once settled' for final reply. It doesn't describe error handling or output format, but given the simple fetch operation, it's sufficient. A 4 seems appropriate.
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 already describes run_id as 'A run id (trun_...).' The description does not add additional meaning beyond implying it identifies the run. Since schema coverage is 100%, baseline is 3.
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 (Fetch) and resource (a run), listing the data returned (status, summary, approvals, final reply). It distinguishes from siblings like list_runs because it fetches a single run by ID.
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?
Implies usage: you need a run_id to fetch details. It doesn't explicitly contrast with list_runs or get_chat, but the name and parameter make the use case clear. No explicit exclusions, so it's a 4 for clear context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool maps to a distinct resource-action pair: REST execution, endpoint discovery, chat/run lifecycle, approvals, and identity. Even similar tools like get_run and wait_for_run are clearly separated by blocking vs. non-blocking behavior.
Most tools follow a clear snake_case verb_noun pattern (get_run, list_chats, send_message, cancel_run). Minor deviations like api_execute, api_search, ask_crevio, and whoami keep the set readable but prevent a perfect consistency score.
Fourteen tools is within the well-scoped range and each tool has a meaningful role across API access, run management, chat interaction, approvals, and account identity. No obvious bloat or redundant duplicates.
The generic api_execute tool provides broad REST API coverage, and run/chat lifecycle tools are nearly complete. The ask_crevio description references a start_task tool that does not exist, though start_chat offers a workaround for launching runs without waiting.