integrate_samples

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

The annotation destructiveHint: true signals the operation may alter or destroy data, but the description adds no context about what gets destroyed (e.g., whether original samples are modified, whether integration is reversible). While there's no annotation contradiction, the description misses the opportunity to disclose side effects, GPU/resource usage, or runtime expectations, which are especially important given the destructive hint.

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 reasonably concise but wastes space on an 'Args:' block that largely duplicates schema information. A more streamlined version could have eliminated the redundant parameter list and focused on the tool's outcome, edge cases, or side effects. Still, it's not overly verbose.

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 destructiveHint and complex parameter set, the description is incomplete. It doesn't explain output format (or if there is one), failure modes (e.g., what if data_ids has duplicates or incompatible datasets), or the impact of integration (e.g., does it return a new object, modify in place, or write to disk?). The presence of an output schema reduces the need to describe return values but doesn't excuse the lack of side-effect disclosure.

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?

The description mentions 'method, batch_key, n_pcs' which are already well-documented in the schema with defaults and descriptions. The description adds marginal value by signaling these are the key parameters but doesn't explain their semantics or interaction. With 50% schema coverage (data_ids and params), the description partially compensates but doesn't fully close the gap.

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 uniquely identifies the tool's purpose with a specific verb and resource: 'Integrate multiple spatial transcriptomics samples into a unified dataset.' It clearly differentiates from sibling tools focused on loading, preprocessing, or visualization since none of them imply data merging/integration at scale.

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 clear context that this tool is for integrating multiple samples, implying it's for batch processing scenarios. However, it doesn't explicitly state alternatives or exclusion criteria like 'for a single sample, use load_data.' The need for 2+ samples is implied by the schema's minItems but not spelled out in prose.

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