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

Beyond the annotations (read-only, idempotent, non-destructive), the description discloses the retrieval mechanism ('indexed lexical matching with vector retrieval'), what is returned ('stable typed IDs, ids_by_type, detail_tool/detail_arguments, and selection hints'), and how to use ArtDirection results ('use the returned art_direction_id in briefs'). This adds substantial behavioral context not present in the structured data.

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?

Three dense, information-packed sentences that front-load the core purpose and scope, then provide usage guidance, return-value summary, and technical detail. Every sentence earns its place without redundancy, and the structure is logical: scope → when to use → workflow → return semantics → technical mechanism.

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's complexity (multiple item types, hybrid retrieval, no output schema), the description is remarkably complete. It explains the return format, integration with list_outfits and propose_outfits, how to handle ArtDirections in briefs, and the internal retrieval methodology. Combined with the rich input schema and annotations, it provides all needed context for an AI agent to select and use the tool 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?

Input schema has 100% coverage with descriptive parameter names and explanations (e.g., 'Hybrid retrieval query. Handles exact names/SKUs/IDs and natural-language visual or attribute intent'). The description adds no additional parameter-level detail, but reinforces the query semantics with examples. Baselines at 3 given full schema coverage; no more credit warranted.

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 performs 'universal hybrid retrieval' across the user's visible Uwear library, naming specific resource types (garments, avatars/models, locations, ArtDirections, uploaded files, generation results). It distinguishes itself from sibling tools by specifying 'use this before opening the picker' and 'do not run separate substring searches', making its unique role and scope unambiguous.

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 tells when to use the tool (when user describes assets by exact name/SKU or natural language) and provides concrete examples. It also gives clear alternatives for specific scenarios, such as 'retrieve matching garments first, then call list_outfits with clothing_item_ids or propose_outfits from the garment IDs', and warns against redundant substring searches. This fully addresses usage versus alternatives.

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