Call stack

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

With no annotations, the description carries the full behavioral burden. It does disclose the key trait — the result is only meaningful 'at the current pause' — which is real context beyond the schema. It says nothing about failure behavior when not paused, whether the result is a structured array or formatted text, or ordering (top frame first vs. last).

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?

Two compact sentences: the first defines the payload and its fields, the second explains how the output is consumed. Nothing is padded and the core content is front-loaded.

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?

There is no output schema, so the description must describe the return shape, and it does so concretely (frame index, function name, file:line:col) while flagging the pause precondition. The remaining gap is edge-case behavior when the debugger is not paused, which is minor for a no-argument read of current debugger state.

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 tool takes zero parameters, so the baseline is 4 and there is no parameter semantics to document or omit. The description correctly adds nothing here rather than inventing inputs.

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?

States the exact resource (the full call stack) and enumerates the returned fields (frame index, function name, file:line:col), with the scope condition 'at the current pause'. This is enough to distinguish it from sibling readers like get_scopes, get_properties, and get_output, though the distinction is inferred from content rather than stated as an explicit contrast.

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 'at the current pause' implies the tool only makes sense while execution is stopped, and naming get_scopes/evaluate as consumers of frame indices hints at the downstream workflow. However, there is no explicit when-to-use statement, no stated prerequisite that the debugger must be paused, and no guidance on what to do if it is not.

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