summarize-experiment

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

Annotations already indicate readOnlyHint=true and openWorldHint=true, establishing safety and openness. Description adds behavioral context about the composite nature (overview + topN + stats) but does not introduce new safety concerns or contradictions.

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?

Description is a single, front-loaded sentence that conveys the tool's value proposition efficiently without waste. Every part earns its place.

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 no output schema, description adequately covers the main use case (overview, topN, stats). It does not specify error cases or exact response structure, but the parameter count (5) is manageable and parameters are well-documented. Completeness is high but not exhaustive.

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% with descriptions for all 5 parameters. Description adds context for 'topN' (default 5, max 20), 'metric' (sorts by start_time if omitted), and 'ascending' (only meaningful with metric), but these details are largely present in the schema. Baseline 3 is appropriate.

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?

Description clearly states it provides an aggregated experiment view with overview, topN runs sorted by metric or start_time, and metric stats, replacing multiple round-trips. It distinguishes itself from siblings like get-experiment, search-runs, and get-best-run by explicitly naming them as alternatives.

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?

Description specifies when to use this tool (to replace 3-5 round-trips) and implies it's for getting a composite view. However, it does not explicitly state when not to use it or list other alternatives beyond the mentioned ones.

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