execute_probe

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

Annotations already mark the tool as not read-only and not destructive; the description adds that it persists evidence, limits output ('bounded'), and redacts it, and that exactly one probe is executed. This gives the agent a meaningful safety/effect profile beyond the structured hints.

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?

A single front-loaded sentence contains the action, scope, and output behavior with no filler. Every word contributes to the decision to invoke the tool.

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 5-required-parameter workflow tool, the description plus fully documented schema and output schema cover most invocation needs. It could explicitly state the prerequisite flow from prepare_probe, but the parameter descriptions already name prepare_probe as the source of plan_id and approval_token.

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?

All five parameters are fully described in the schema (100% coverage), so the description does not need to define each one. It only loosely maps 'approved' to the approval parameters and says nothing about diagnosis_id or plan_id beyond the schema.

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 opens with a specific verb-object pair ('execute one approved argv probe') and adds a concrete outcome ('persist bounded, redacted output evidence'). This clearly distinguishes execution from prepare_probe and other diagnosis/probe siblings without requiring schema inspection.

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 word 'approved' and the presence of approval_token/plan_id in the schema imply this is the post-approval execution step, but the description never states 'use after prepare_probe' or contrasts it with run_preflight/analyze_failures. Usage is inferred rather than explicit.

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