select_frame

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

Without annotations, the description fully discloses the behavioral effect: it changes the context for subsequent inspection commands. No contradictions or hidden side effects are present.

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?

Extremely concise: two sentences with no fluff. The first sentence states the action, the second provides context and effect. Every sentence earns its place.

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 simple selection tool with two parameters and an output schema, the description covers purpose, usage guidance, and effect. It doesn't need to describe return values since output schema exists. The mention of backtrace ensures the agent knows the prerequisite.

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 description adds meaning to the frame parameter (it's a number, 0 is innermost), but session_id is not explained. With 0% schema coverage, the description should at least mention session_id's role, though it's a common parameter across tools. The added value partially compensates but not fully.

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?

Description clearly states it selects a stack frame by number, referencing GDB 'frame N'. It explains the special case of frame 0 and the effect on inspection commands, making it distinct from siblings like backtrace or up/down.

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?

Explicitly advises to use backtrace to see frame numbers first, and explains that after selection, inspection commands operate in that frame's context. This provides clear context, though it could mention alternatives like up/down for relative movement.

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