keel_strategy_compose

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

The description adds significant behavioral context beyond annotations: dry_run behavior, validation feedback always returned, validation does not block save, DSL constraints (no import, pipeline normalizer requirement), and references to other tools for help. Annotations already indicate idempotent and non-destructive, and the description aligns without contradiction, enriching the safety profile.

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 long but each sentence earns its place by adding critical guidance, constraints, or references. It is front-loaded with the core action and then builds context. Minor redundancy (e.g., 'exactly one' restated) but overall efficient for the complexity.

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 complexity (6 parameters, output schema, dry_run mode, update vs. create), the description is fully comprehensive. It covers validation behavior, DSL constraints, first-time workflow, and alternatives. Output schema exists, so return values are presumably documented there, making the description complete.

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%, and the description adds crucial context: exactly one of source or source_file required, dry_run purpose to iterate cheaply, parent_version as optional commit ref, and validation feedback structure. This goes beyond the schema's property descriptions, fully clarifying parameter usage.

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 purpose: 'Create or update a strategy from DSL source.' It distinguishes between create (no strategy_id) and update (with strategy_id), and introduces the dry_run mode. This differentiates it from sibling tools like fork or delete.

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 provides explicit when-to-use guidance: use dry_run first for cheap iteration, invoke the strategy-creation prompt for first-time composing, and use strategy-fork-and-iterate for modifying an existing strategy. It also states what NOT to use (fork, backtest), making it exceptionally clear.

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