compute_embeddings

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

Annotations (readOnlyHint=false, idempotentHint=false) indicate mutation and non-idempotency, but the description fails to disclose side effects, such as whether previous results are overwritten (the 'force' parameter hints at this but is not explained). No mention of data persistence or performance impact.

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 short but includes an 'Args' block that redundantly lists parameter names. Front-loading the purpose is good, but the Args section adds no value beyond the schema. Could be more concise without losing information.

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 complexity (multiple computational steps like PCA, neighbors, UMAP, clustering) and the availability of an output schema, the description is incomplete. It does not mention the output format (e.g., modifies the dataset in memory) or the dependencies between steps (though schema descriptions cover some). A more complete description would improve usability.

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 0%, meaning the description does not explain parameters. Although the schema itself has detailed parameter descriptions (nested in EmbeddingParameters), the tool description merely lists parameter names without adding meaning. For low coverage, the description should compensate, but it does not.

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 clearly states the tool's purpose: 'Compute dimensionality reduction (PCA, UMAP), clustering, and neighbor graphs.' It uses specific verbs and resources, and the sibling list shows no other tool with overlapping functionality, making it distinct.

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 provides no guidance on when to use this tool versus alternatives, nor does it list prerequisites (e.g., preprocessed data) or conditions to avoid. Without such context, the agent may misuse the tool.

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