analyze_velocity_data

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

Annotations indicate readOnlyHint=false, meaning the tool modifies data, but the description does not disclose what changes occur (e.g., whether it adds a velocity layer or modifies the object). It adds no behavioral context beyond the annotations, which already imply mutation.

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 concise with two sentences and a brief Args list. It front-loads the main purpose and requirement. However, the Args section is somewhat informal and could be more structured (e.g., using code formatting). Overall, it is efficient but slightly loose.

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?

Despite having an output schema, the description does not hint at return values. It omits side effects (mutating data, given readOnlyHint=false), default behavior when params is null, and prerequisites beyond the layers. For a tool with a nested parameter object, this is incomplete.

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 parameters (data_id, params) have no schema descriptions (0% coverage). The description adds minimal help: 'Dataset ID' and 'Velocity parameters (method, scvelo_mode, etc.)', but does not explain that params is optional, its nested structure defaults, or how the example fields relate to parameter selection. The nested object itself has good schema descriptions, but the top-level lacks.

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 'Analyze RNA velocity to understand cellular dynamics', specifying the verb 'analyze' and the resource 'RNA velocity'. It also mentions the critical requirement of 'spliced' and 'unspliced' layers, which distinguishes it from siblings like 'analyze_trajectory_data' that likely handle general trajectory inference.

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 only mentions the requirement for specific data layers but provides no guidance on when to use this tool vs alternatives such as 'analyze_trajectory_data' or when not to use it. No explicit context for selection among siblings is given.

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