recommend_next

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 explains that passing source_id runs quick EDA if no run is cached, run_id reads from artifact, and return values come with full args ready to invoke. This adds meaningful context beyond what a schema or annotations would provide.

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 compact, front-loaded with the key outcome, and uses formatting (bold, code) to emphasize important terms. Every sentence adds value with no redundancies.

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 tool has an output schema, so return structure need not be fully described. The description covers input alternatives and a key behavioral trait (pre-filled args). Given the moderate complexity and the presence of many sibling tools, it is sufficiently complete for an agent to decide when and how to invoke it.

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%, so the description must clarify parameters. It explains source_id and run_id semantics, but does not explain `hints`. This partial compensation is adequate but leaves one parameter undocumented.

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: 'Return ranked, pre-filled next-action tool calls.' It uses a specific verb (Return) and resource (next-action tool calls), and the 'pre-filled' detail distinguishes it from sibling tools like recommend_tasks.

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 gives clear usage context by explaining when to pass source_id versus run_id, and notes it is designed for local models picking from a numbered menu. It doesn't explicitly exclude alternatives, but the parameter guidance is actionable and implies when this tool is appropriate.

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