compute_embeddings

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

Annotations already declare destructiveHint=true, so there is no contradiction. However, the description adds no behavioral context beyond the annotation—it does not mention overwriting existing results, storing outputs in the dataset, or dependencies like UMAP requiring neighbors.

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 with the core operations front-loaded. No filler or redundant content.

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?

Given the complex nested params object and destructive behavior, the description is only a brief headline. It omits parameter dependencies, side effects, and usage context, leaving the agent under-informed for such a configurable tool.

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?

Top-level schema coverage is 0%, and the description only provides one-line glosses for data_id and params. The rich descriptions live inside the nested EmbeddingParameters schema, which the description does not surface or summarize effectively.

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 opens with 'Compute dimensionality reduction (PCA, UMAP), clustering, and neighbor graphs,' which uses a specific verb and names concrete resources. It clearly distinguishes this from sibling tools focused on trajectory or spatial analysis.

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?

There is no guidance on when to use this tool versus siblings like analyze_trajectory_data or preprocess_data. The description lists operations but does not mention prerequisites, typical use cases, or exclusions.

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