compare_conditions

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

Annotations indicate readOnlyHint=false (may modify) and idempotentHint=true (safe to repeat). The brief main description does not add behavioral context beyond these annotations, such as whether results are stored or returned, or any side effects. It does not contradict annotations, but provides minimal extra transparency.

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 exceptionally concise (two sentences) and well-structured with a clear purpose and an 'Args:' list. Every word serves a purpose with no repetition or fluff.

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 complexity (multiple parameters, sibling tools), the main description lacks information about output/return values (even though an output schema exists), error conditions, or prerequisites beyond minimum samples. The params description in the schema compensates partially, but the tool description itself is incomplete for an agent to fully understand what to expect.

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 main description lists key required sub-parameters (condition_key, condition1, condition2, sample_key) within an 'Args' style, adding value beyond the schema which has 0% coverage at the top level. However, the nested schema already provides detailed descriptions for all parameters, so the main description is helpful but not essential.

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 'Compare experimental conditions using pseudobulk differential expression (DESeq2).' This specifies the verb (compare), resource (experimental conditions), and method (DESeq2). The params schema further differentiates from sibling find_markers by contrasting within-dataset cell type comparisons vs across-sample condition comparisons, providing strong distinction.

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 explicitly contrasts with find_markers in the params definition: 'Key difference: find_markers compares cell types within a dataset, compare_conditions compares conditions across samples.' This provides clear when-to-use and when-not-to-use guidance. Additional constraints like requiring 2+ samples per condition further inform usage.

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