scaffold_strategy

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

With no annotations, the description carries full burden. It discloses that the output is a compilable starter class and that it includes a Next steps section. It doesn't explicitly state that the tool is read-only (no side effects), but the nature of generating code implies no destructive actions. The description is transparent enough for an agent to understand behavior.

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 informative but somewhat lengthy. Each sentence adds value, and it is front-loaded with the core purpose. However, some phrases like 'instead of writing the FLOX bookkeeping...' could be considered slightly redundant given the main purpose. Still, it is well-structured for practical use.

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, the description adequately explains the return value: a starter strategy class that compiles and passes validate_strategy, with a Next steps section containing docs_search queries. It also covers parameter semantics and usage context. The tool is complex, but the description provides sufficient completeness for an 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 coverage is 100% with descriptions for all three parameters. The description adds significant value: it explains why 'language' is required (FLOX is polyglot, ask user), clarifies the three kinds of 'kind' (bar-driven, trade-driven, hybrid), and notes defaults. This goes 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 returns a starter FLOX strategy class that compiles and passes validate_strategy, using specific verb ('Return') and resource ('starter FLOX strategy class'). It distinguishes from siblings like validate_strategy or compute_indicator by positioning itself as the first step when building a new strategy.

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?

Explicitly tells when to use: 'as the *first* thing you write when the user asks to build a new strategy'. Provides exclusion guidance: 'picking the binding for the user is wrong; ask which language they want first'. Also gives context on the three kinds and subsequent steps with docs_search queries.

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