compare_strategy_experiments

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

With no annotations provided, the description carries the behavioral burden. It explicitly states 'Read-only and does not access TradingView', which discloses side-effect profile and external dependencies. It also describes a behavioral constraint: no ranking or combining. It does not mention what happens with invalid references or duplicate entries, but the core transparency is above average.

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?

Two sentences, front-loaded with the core action and scope, followed by essential constraints. Every clause earns its place: count range, no ranking/combining, required fields, and read-only guarantee. No redundancy or vague filler.

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?

For a read-only comparison tool with one parameter and no output schema, the description covers invocation requirements and behavioral boundaries well. The only notable gaps are the lack of explicit sibling differentiation and no hint about the return format, though 'compare' implies a comparative result. Overall, it is sufficiently complete for a capable agent.

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%, so the description must compensate. It does: it explains the references array accepts 2–20 items and each reference must contain both experiment_id and evidence_hash. It omits the exact object shape but the schema itself provides the pattern constraints, so the textual guidance is meaningful and adequate.

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 verb 'Compare' and the resource 'saved experiment-evidence records', and adds a scope of 'two to twenty'. It also notes what the tool does not do ('without ranking or combining incompatible populations'). However, it does not explicitly name or distinguish the closely-related sibling tool 'compare_research_evidence', so it falls just short of full sibling differentiation.

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 gives clear conditions for use: 'exact saved experiment-evidence records' and 'References must include both experiment_id and evidence_hash'. It also provides an exclusion, noting the tool works 'without ranking or combining incompatible populations', implying those operations are not appropriate here. It stops short of explicitly naming alternative tools for those cases.

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