train_bertopic

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

No annotations provided. The description mentions training with UMAP+HDBSCAN and automatic topic discovery, but fails to disclose key behaviors: whether it replaces an existing model, required input documents, side effects, or output format. Critical gaps for a training tool.

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?

Two concise sentences, front-loaded with the primary action. No redundant information. Could be slightly more structured, but adequate.

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?

No output schema or description of return values. The agent is left uninformed about what the tool returns (model object, topics list, etc.). Also lacks integration guidance with sibling tools. Incomplete for a training function with no output specification.

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 both parameters (num_topics, min_cluster_size) having clear descriptions and defaults. The description adds general context about algorithms but no additional meaning beyond the schema. Baseline score of 3 is appropriate.

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 states 'Train BERTopic model using document embeddings' with a specific verb and resource, distinguishing it from sibling tools like train_lda_topics, train_nmf_topics, and clustering tools by mentioning unique algorithms (UMAP+HDBSCAN).

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?

No guidance on when to use this tool versus alternatives like train_lda_topics or cluster_documents_hdbscan. The description does not specify prerequisites, limitations, or scenarios where this tool is preferred.

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