update_stage_model

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It clearly states that changes are applied immediately (in-memory) and persisted to config/default.toml, and notes the prerequisite that the model must exist in the catalog. It also indicates the return type (confirmation). This is meaningful behavioral context beyond the basic 'update' semantics.

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 concise and well-structured with a brief summary, Args section, and Returns statement. Every sentence adds value, and the docstring format makes key information easy to parse. No fluff or redundancy.

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 simple two-parameter mutation tool, the description covers all essential aspects: purpose, prerequisites, immediate effect, persistence, and return value. Given the presence of an output schema, the 'Returns: Confirmation' is sufficient. The tool is simple enough that this description is fully 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 description coverage is 0%, but the description compensates well by documenting both parameters: 'stage' with its allowed values ('extraction', 'reasoning', 'matching') and 'model_name' with concrete examples. This adds significant meaning beyond the bare schema, though it stops short of explaining the semantics of each stage value.

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 function: 'Change the default LLM model for a pipeline stage.' This uses a specific verb ('Change') and resource ('default LLM model for a pipeline stage'), distinguishing it from siblings like add_catalog_model (which adds to the catalog) and update_fallback_chain (which updates fallback chains).

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 clear contextual guidance: the model must already exist in the catalog and changes are applied immediately and persisted. While it doesn't explicitly mention alternatives or exclusions, the context is sufficient for an agent to know when to use this tool, especially with sibling tools like add_catalog_model implicitly being a prerequisite.

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