screen_universe

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

Annotations already provide readOnlyHint=true, so the safe read behavior is covered. The description adds valuable behavior context: the catalog/training-data restriction, the fact that results include computed metrics per asset, and the operator/field semantics. It omits pagination/rate limits, but the annotation coverage lowers the burden.

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 dense but well-structured and front-loaded. The purpose statement, scope limitation, field catalog, operator rules, and downstream workflow are all necessary for a screening tool with four parameters and many possible criteria. There is no filler or 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 presence of an output schema and annotations, the description is complete for correct invocation: it explains prerequisites, alternative tools, all field families, allowed operators, sorting/limit defaults, and what results contain. This is a comprehensive, self-sufficient description.

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?

Although the schema has 100% description coverage, the description goes further by enumerating valid metadata fields, price fields, and the exact operator families allowed for each type (eq/neq/in vs gt/gte/lt/lte/between). It also clarifies default sort behavior, adding real meaning beyond the schema definitions.

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 opens with a specific verb and resource: 'Screen the asset universe by metadata and price-based metrics.' It clearly distinguishes this tool from catalog-expansion tools like search_features/add_feature by stating it only operates on assets already in the Sablier catalog, and from market overview tools by listing concrete screening fields and operators.

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?

It explicitly states when to use the tool: only for assets already in the catalog with training data, and tells the agent to 'Use search_features + add_feature first to expand the catalog if needed.' It also gives a downstream workflow suggestion ('Use top results to create a portfolio'). It does not explicitly contrast with other possible screening-like siblings such as market_radar, so it stops short of a 5.

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