detect_conversational_piiMulti-turn PII detection with cross-turn coreference.
Brainiall Conversational PII engine. Same surface text + type across turns gets the same entity_id.
| Name | Required | Description | Default |
|---|---|---|---|
| turns | Yes | List of [role, content] dicts representing a dialogue |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover the safety profile (readOnly, idempotent, openWorld, non-destructive), so the bar is lower. The description adds genuinely useful behavior beyond annotations: cross-turn coreference and the rule that 'Same surface text + type across turns gets the same entity_id.' The 'Brainiall Conversational PII engine' sentence is branding noise, but the entity_id disclosure earns the score.
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 core purpose is front-loaded in the first sentence, and the entity_id detail is a compact high-value addition. One sentence ('Brainiall Conversational PII engine.') carries no informational value and costs a point.
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?
There is no output schema, and the description does not explain what the tool returns beyond implying entity_ids — an agent cannot anticipate the response shape (entity types, positions, confidence scores). With one well-documented parameter and safety annotations covering behavior, this is adequate but has a real gap around return semantics.
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% — the schema already documents turns as 'List of [role, content] dicts representing a dialogue.' The description's entity_id rule pertains to output behavior, not parameter meaning, so the baseline 3 applies without the description needing to compensate.
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 and resource ('Multi-turn PII detection') and adds a distinguishing behavior ('cross-turn coreference') that sets it apart from the sibling detect_pii. The entity_id stability rule further clarifies exactly what this tool does that its single-turn sibling does not.
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 'multi-turn' qualifier and 'cross-turn' language imply this tool is for dialogue contexts, presumably as opposed to detect_pii for single texts. However, no alternative is named explicitly and no when-not-to-use condition is stated — the routing is left to inference.
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.