REACT/BAE report-back for cue status, active variables, skipped bindings, capability misses, last_frame_at, and errors.
| Name | Required | Description | Default |
|---|---|---|---|
| error | No | ||
| status | No | ACTIVE, STOP_REQUESTED, or STOPPED | |
| launch_id | Yes | The launch_id to report | |
| executor_id | No | ||
| last_frame_at | No | ||
| active_variables | No | Variables actually being sampled by REACT/BAE | |
| skipped_bindings | No | ||
| capability_misses | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations provide readOnlyHint=false and destructiveHint=false, and the description does not contradict these. The description adds context by enumerating the fields reported, but it does not disclose side effects (e.g., whether this overwrites prior state), authentication requirements, or idempotency. This meets the baseline with annotations but lacks rich behavioral detail.
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 a single sentence, front-loaded with the core action and then a concise enumeration of the report's contents. Every word contributes to describing the tool's purpose and payload, with no redundant or irrelevant text.
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 tool with 8 parameters, nested objects, and no output schema, the description gives the essential idea and data fields but lacks important operational context: it does not mention the required launch_id, how the report is delivered, or when it should be called. It is adequate for a basic understanding but not fully complete.
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 38%, and the description compensates by naming several parameters (status, active_variables, skipped_bindings, capability_misses, last_frame_at, errors), giving semantic meaning to those without schema descriptions. However, it omits launch_id and executor_id, so compensation is partial.
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 explicitly names the action ('report-back'), the resource ('lighting cue'), and the specific data payload (status, active variables, skipped bindings, capability misses, last_frame_at, errors), making it clear this tool is for reporting execution results. This distinguishes it from siblings like ack_lighting_cue (acknowledgement) and get_lighting_cue (retrieval).
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 description implies usage (REACT/BAE report-back) but gives no explicit guidance on when to invoke this tool versus alternatives, no prerequisites, and no mention of how it relates to launch_lighting_cue or stop_lighting_cue. Users must infer the intended workflow.
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.
Every tool targets a distinct action or resource. Groups like compels, lighting cues, webhooks, and account are clearly separated, and even similar tools (create_compel vs create_compel_from_music) have well-defined differences in input source.
All tool names follow a consistent verb_noun pattern with underscores (e.g., cancel_compel, launch_lighting_cue, register_webhook). No mixing of conventions or ambiguous verb choices.
With 30 tools, the server is above the 25+ threshold for 'too many'. While the scope includes multiple subdomains, the high number adds cognitive load and risks selection errors for an agent.
Core workflows are present (create, read, cancel, list, search, render), but missing update/delete for compels and media, and no way to modify render configuration beyond defaults.