next_best_action

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

Without annotations, the description carries the burden. 'Calculate and recommend' suggests a read-only operation, and listing the factors adds behavioral context, but it doesn't explicitly state that it makes no modifications, what the output contains (though output schema may cover that), or how 'file hints' are used.

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?

A single sentence that is easy to parse and front-loaded with the main action. The word 'Intelligently' is minor filler but doesn't detract much.

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 recommendation tool with complex inputs and sibling tools like 'next_task', the description is under-specified: it doesn't explain the role of 'path', the difference from 'next_task', or what constitutes 'file hints'. With output schema present, some return details may be covered, but the overall context is incomplete.

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 one parameter 'path' with no description (0% coverage), and the description never mentions 'path' or how it relates to 'file hints'. This is a significant gap; the agent must guess what path means.

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: it calculates and recommends the next best task using phase, priority, dependencies, and file hints. This is a specific verb+resource, though it doesn't explicitly differentiate itself from the sibling tool 'next_task'.

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 phrase 'based on phase, priority, dependencies, and file hints' implies when to use it (when these factors matter), but there's no explicit comparison to alternatives like 'next_task' or 'list_tasks', nor any 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.