Cross-Disease Structural Target Overlap

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

Annotations provide readOnlyHint, idempotentHint, openWorldHint. Description adds specific return structure (shared/unique targets, Jaccard score). No contradictions. Adds useful behavioral context beyond annotations.

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?

Well-structured: short intro, bullet points for returns, example. No redundant sentences. Every part serves a purpose and is easy to scan.

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?

Covers core functionality and return structure. Output schema exists, so return explanation is sufficient. Missing explanation for 'target_limit' parameter detracts slightly, but overall complete for agent to invoke correctly.

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 coverage is 0% (minimal descriptions). Description does not explain parameter semantics beyond example showing Alzheimer and Parkinson IDs. 'target_limit' parameter is mentioned but not explained; its purpose (max number of targets to return) is only in schema. Should add description of target_limit and clarify format of MONDO IDs.

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?

Description clearly states it compares protein target landscapes of two diseases, identifies shared/unique targets, and computes Jaccard similarity. Title 'Cross-Disease Structural Target Overlap' and example reinforce purpose. Distinguishes from siblings like get_disease_targets (single disease) and get_common_disease_targets (likely different).

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?

Explicitly states use cases: drug repurposing, identifying shared mechanisms, comorbidity. Example with Alzheimer and Parkinson clarifies context. Does not explicitly state when not to use or list alternatives, but clear enough for selection among siblings.

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