Varrd

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

Annotations confirm read-only/idempotent safety. Description adds crucial context absent from annotations: exact return structure (dollar entry/stop/take-profit prices), behavioral characteristic ('validated statistical model'), and precision guarantees. No contradictions with readOnlyHint=true.

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, zero waste: Sentence 1 states purpose, Sentence 2 details return values (compensating for missing output schema), Sentence 3 establishes quality differentiation. Front-loaded with clear value proposition. No redundancy with schema or annotations.

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?

Robust for a 2-param read operation. Compensates effectively for missing output schema by documenting return fields and data types (exact dollar prices). Annotations cover safety profile. Minor gap: no mention of empty-result behavior when no strategies fire or no saved strategies exist.

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 100%, providing full param documentation. Description reinforces concepts ('current market data' aligns with 'market' param, 'firing right now' aligns with 'only_firing') but adds no syntax, validation, or format details beyond schema. Baseline 3 appropriate per scoring rules for high-coverage schemas.

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: verb 'Scan' + resource 'saved strategies' + scope 'current market data'. Distinguishes from research-oriented siblings (research, autonomous_research, get_hypothesis) by emphasizing 'your saved strategies' vs discovery. Also previews exact return values (entry, stop-loss, take-profit) clarifying output intent.

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?

Strong contextual guidance via 'your saved strategies' and 'what's firing right now,' implying use for monitoring existing setups rather than discovery. Contrasts output precision vs 'vague directional calls.' Lacks explicit sibling alternative naming (e.g., 'use research to find new strategies'), preventing a 5.

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