step_into

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 but provides almost none. It does not state that stepping executes instructions (a side effect), requires an active debugging session, or what happens when no session exists. The phrase 'single step' is the only behavioral hint, but it is insufficient for a mutation-like operation.

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 only five words and is under-specified rather than concise. While it is front-loaded, it wastes the opportunity to convey essential information. Like the 'Process' calibration example, extreme brevity without substance should be penalized.

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 debugging step tool with a parameter and sibling alternatives, the description is critically incomplete. It omits session requirements, function-call behavior, and differentiation from step_over. Although an output schema exists (so return values need not be explained), the definition leaves the agent without enough context to invoke the tool correctly.

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 (session_id) with 0% description coverage, and the tool description does not mention it at all. Since schema coverage is below 50%, the description should compensate by explaining the session_id's role, but it is entirely silent. The parameter's purpose and optional nature are left 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 says 'Step into (single step) (ds),' which identifies a stepping action but does not specify what is stepped into (e.g., a function call) or distinguish it from the sibling step_over. The parenthetical '(ds)' is cryptic and adds no clarity. The agent can infer a debugger step operation from the tool name alone, but the description provides only a vague purpose.

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?

There is no guidance on when to use step_into versus alternatives like step_over or continue_execution. No prerequisites (e.g., an active session) or context for invocation are given. The description merely names the operation without usage context.

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