Compare two configurations over the same seeds

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

Annotations declare readOnlyHint=true, and the description does not contradict. It adds behavioral context: paired experimental design cancels terrain and emplacement luck, and it returns a plain-language summary. No destructive behavior indicated.

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 a single paragraph that is dense but efficient, front-loading the purpose and including all key information (paired design, output types, max count, example). It could be restructured slightly for readability but is not overly verbose.

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 tool's complexity (6 parameters, nested objects, no output schema), the description adequately covers the return values and the experimental design. It provides enough context for an AI agent to use it appropriately, though it could describe the output format more explicitly.

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 parameters and nested fields. The description adds extra context like 'deterministic' and example seeds, and explains that config values can be '{} for the stock configuration', enhancing understanding beyond the schema.

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 tool's action: 'Run two CONFIG variants over the SAME consecutive seed range' and specifies outputs (aggregate statistics, paired deltas, flipped seeds, plain-language summary). It distinguishes itself from siblings like sweep_seeds (single config) and run_engagement (single run).

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?

The description gives an explicit use case example ('test doctrine questions, e.g. what happens to win rates when OPFOR adopts EMCON discipline') and mentions the 'Max count 500' limit. It implies when to use but doesn't explicitly state alternatives or when not to use.

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