classify_text_customZero-shot text classification — define your labels at call time. No training, no data upload.
Brainiall Custom Classifier engine. Returns {top_label, scores, confidence}.
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | Input text | |
| labels | Yes | Your candidate labels (2-20 of them) | |
| multi_label | No | If True, multiple labels can apply |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly and idempotent hints, and the description adds valuable behavioral detail: it explicitly states the zero-shot nature, that no training or data upload occurs, and it discloses the return shape ({top_label, scores, confidence}). Since there is no output schema, this return format disclosure is especially informative.
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 compact and front-loaded: the first sentence conveys the core purpose and differentiator, and the second line adds the return format. Every clause earns its place with no filler.
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?
The description is complete for this tool's needs. It covers return values (since no output schema exists), relies on a fully documented input schema, and the annotations handle safety and idempotency. An agent can correctly select and invoke the tool with the information provided.
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 description coverage is 100%, with text, labels, and multi_label all already documented. The description adds no new parameter-level detail beyond the schema, so the baseline score of 3 applies.
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 states a specific verb+resource: zero-shot text classification with user-defined labels at call time. The phrase 'define your labels at call time' clearly differentiates this from sibling classifiers like analyze_sentiment or analyze_toxicity, which use fixed, predefined label sets.
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 a clear use case: custom classification without training or data upload, which signals when to use this over purpose-built classifiers. However, it does not explicitly name alternatives or state when not to use the tool, so it stops short of full exclusion guidance.
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.
Most tools map cleanly to distinct capabilities, and the descriptions make the intended use clear. A few adjacent pairs—extract_entities vs link_entities_to_wikidata and detect_pii vs detect_conversational_pii—require careful selection, but they are distinguishable by their stated outputs.
Names are uniformly lowercase snake_case and mostly follow a verb_object pattern, such as analyze_*, detect_*, extract_*, summarize_text, and translate_text. A few outliers like aspect_sentiment, fraud_feedback, and knowledge_ingest break the verb-first feel, but the overall pattern remains predictable.
At 22 tools, this is on the heavy side of the borderline range. Each tool has a distinct job, but the mix of core NLP, safety, fraud, health-checking, and knowledge-base management makes the surface feel sprawling rather than tightly scoped.
The core NLP coverage is broad: sentiment, toxicity, PII, entities, QA, summarization, translation, and groundedness are all present. However, the knowledge-base tools support ingest/list/query but no delete or update, creating a dead end when documents need correction or removal.