Varrd

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

Adds valuable behavioral detail beyond annotations: describes ranking ('ranked by relevance') and specific returned data points ('win rate, Sharpe, edge status'). Annotations cover the read-only safety profile (readOnlyHint=true, destructiveHint=false), allowing the description to focus on business-logic behavior rather than safety warnings.

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 sentences with zero waste: (1) Core action + method, (2) Return format + ranking, (3) Usage context. Perfectly front-loaded and dense with actionable information. No filler or tautology.

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?

Appropriate for tool complexity: describes the search scope, ranking behavior, and return statistics despite lacking an output schema. The 100% schema coverage handles parameter specifics, leaving the description free to focus on domain context. Minor gap: could mention pagination behavior or maximum result limits.

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?

While schema coverage is 100% (baseline 3), the description adds semantic value by reinforcing the natural language capability ('natural language query') and connecting the query parameter to the specific domain ('saved hypotheses'). It doesn't detail the optional 'market' filter or 'limit', but the schema handles those adequately.

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?

Excellent specificity: 'Search your saved hypotheses' clearly identifies the verb (Search), resource (saved hypotheses), and scope (user's own validated strategies). It distinguishes effectively from siblings like 'research' (new investigation) and 'get_hypothesis' (single retrieval) by emphasizing the user's existing validated strategies.

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?

Provides clear usage context: 'Use this to find strategies you've already validated' establishes the retrieval-use-case vs. creation. However, it stops short of explicitly naming alternatives (e.g., 'for new research, use the research tool instead') or stating exclusion criteria.

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