capture_state

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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so the safety profile is covered structurally. The description adds real behavioral value beyond that by disclosing the exact payload composition and the decoding (symbol-resolved backtrace/locals), plus the implicit requirement that the target be halted. It stops short of describing formatting, truncation, or pagination.

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 with zero filler, front-loaded with the 'where am I' framing so the agent immediately grasps the intent. Every clause earns its place by naming a concrete returned artifact.

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?

With no output schema, the description carries the burden of describing the return value, and it does so concretely (registers, PC/LR/SP, backtrace, locals). Combined with annotations covering safety and idempotency, an agent has enough to call it correctly; only edge cases like a non-halted target or empty stack are unaddressed.

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?

There is a single optional parameter with 100% schema description coverage ('Optional debug-session name. Omit for the default target.'), so the schema fully documents it. The description adds no parameter-level detail, which is the correct baseline when the schema does the work.

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 states a specific verb+resource ('One-call "where am I"') and enumerates exactly what it returns: decoded core registers, a PC/LR/SP summary, a decoded backtrace, and innermost-frame locals. It reads as an aggregate snapshot tool, but it does not name the sibling tools it consolidates (read_call_stack, read_registers, analyze_stack), so differentiation is implicit rather than explicit.

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?

It gives a usage context ('the fastest way to get full halted context') that implies you call it when you want a complete halted picture in one shot. However, it names no alternatives and no exclusions, so an agent must infer when a narrower sibling like read_call_stack or read_registers is preferable.

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