update_fallback_chain

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

With no annotations provided, the description carries the full burden, and it does exceptionally well: it discloses the triggering condition, the ordering behavior of fallbacks, the precondition that all models must exist in the catalog, and the effect of an empty string clearing the chain. It also states the return type.

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 well-structured docstring: a one-line purpose, a concise explanation of behavior, parameter definitions, and return statement. Every sentence earns its place, and there is no 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?

Given the simplicity of the tool, the description covers all necessary aspects: both parameters are fully described, the behavioral context is explained, and the return could be inferred from the schema. It is complete and self-contained.

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?

The schema has zero description coverage, but the description fully compensates by defining `stage` with its three allowed values, and `models` with a comma-separated format, an example, and the clearing behavior. This surpasses what a schema enum would provide.

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 opens with 'Set the fallback chain for a pipeline stage,' which is a specific verb + resource combination. It then explains the fallback behavior, clearly distinguishing this tool from siblings like update_stage_model which presumably sets the primary model.

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 usage context: 'When the primary model fails (after retries), the system tries each fallback in order.' This tells when the tool's effect is relevant. It does not explicitly contrast with alternatives like update_stage_model, but the context strongly implies the distinction.

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