mosaic_assess_druggability

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the primary safety profile is clear. The description adds valuable behavioral context: uses AlphaFold + fpocket, returns a coarse structural_tier and interpretation, and is orthogonal to literature. No contradictions with 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?

The description is three sentences: first sentence states purpose, second enumerates outputs, third provides context. It is front-loaded with the verb 'Assess', concise, and every sentence adds value without redundancy.

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 tool has one simple parameter and an output schema is present, the description covers all necessary aspects: it explains what the tool does, what it returns (pockets, scores, tier, interpretation), and how it fits into the broader context (structural vs literature). The output schema can handle detailed return types.

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% (tool description does not mention the parameter), and the single parameter (gene_symbol) is fully documented in the schema itself. The description adds no additional meaning beyond the schema, so it fails to compensate for low coverage.

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 explicitly states 'Assess structural druggability of a target from AlphaFold + fpocket', provides specific outputs (pockets, druggability score, structural_tier), and distinguishes itself from literature-derived heuristics, making the tool's purpose clear and differentiated from siblings like mosaic_get_target_structure or mosaic_find_undruggable_targets.

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 positions the tool as the 'structural answer' to tractability, orthogonal to literature-based heuristics, which implies when to use it. However, it does not explicitly mention alternatives or when not to use, though the context of sibling tools provides some implicit guidance.

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