keil_step_instruction

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

With no annotations, the description carries the burden and does disclose the critical precondition that the target must be halted plus the granularity of the operation. It does not say what happens if the target is running (error vs. auto-halt) or whether state changes are reversible, which matters for a state-mutating debugger call.

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?

One front-loaded sentence that sets the operation, the precondition, and the disambiguation in that order, with no filler.

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 zero-argument tool with an output schema documenting return values, the description covers what the tool does and the state it requires. Only the failure mode when the target is not halted is left unstated.

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 there is nothing for the description to disambiguate; the baseline applies and no parameter meaning is lost.

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 a specific verb ('Execute') and precise unit ('exactly one machine instruction'), and explicitly disclaims the interpretation an agent might default to ('not a source-level step'), which cleanly separates it from keil_step_into/step_over/step_out.

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?

Gives the key precondition ('on a halted target') and an implicit routing rule away from the source-level step siblings, so an agent knows when this is the right tool. It stops short of naming keil_halt or the step_into/step_over alternatives explicitly.

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