recipe_merge

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 mentions 'Waits for completion' which hints at synchronous behavior)Skip but doesn't explain what happens on failure, whether intermediate results are persisted, permission requirements, or how the output checkpoint is created. For a lengthy multi-step operation, critical behaviors like blocking, error handling, and side effects are unspecified.

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, front-loads the core purpose in the first sentence, then provides a compact parameter list. Each sentence earns its place, though some parameter details (e.g., allowed method values) are missing from the text.

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?

The description gives a good overview (multi-step merge, wait-for-completion behavior) and parameter meanings, but omits key details such as the allowed values for 'method' or 'model_type', how the steps chain and whether intermediate results are preserved, and any error/timeout behavior. Since an output schema exists, return values are presumably covered there, but the multi-step merge semantics and options need more depth.

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 property descriptions (coverage 0%), so the description compensates well. It explains each parameter's meaning: model_type as architecture, base_model as checkpoint, output_name as final output, and steps as objects with target_model, method, and alpha (float 0-1). This goes beyond the bare schema and provides the essential semantics needed to invoke the tool correctly.

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: 'Execute a multi-step merge recipe' with each step merging the current result with a new target. This is a specific verb+resource combination that distinguishes it from a single-step merge tool, though it doesn't explicitly name sibling tools like merge_models or batch_merge_models.

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 implies usage context by mentioning 'multi-step' recipe and 'waits for completion', suggesting this is for sequential merges rather than single or batch parallel merges. However, it doesn't explicitly state when to use this vs. merge_models or batch_merge_models, nor any prerequisites or when-not-to-use guidance.

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