Probe Runtime Progress

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

Annotations already declare destructiveHint=true, and the description elaborates on the safety profile by warning that sampling perturbs scheduling and that results are not proof of application-level progress. This is valuable behavioral context beyond the annotations.

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?

Three sentences with no filler: the first states what the tool does, the second gives the trigger condition, and the third gives the exclusion and caveat. 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 probe tool with a rich output schema and annotations, the description covers what it does, when to use it, when not to, and its limitations. Nothing essential is missing for an agent to select and invoke it correctly.

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?

Schema description coverage is 100%, so the schema already documents samples, threadId, sessionId, and intervalMs. The description reinforces the meaning of 'samples' and 'intervalMs' through 'resume/pause intervals', but it does not add substantial parameter-level detail 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 starts with a specific verb and resource ('Sample a live target') and states the diagnostic goal: distinguishing no observed progress, same-frame execution movement, and probable busy loops. It clearly separates this probe tool from snapshot/hang-analysis siblings by framing it as a resume/pause sampling technique.

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 an explicit use case ('when a process appears hung but a single thread snapshot cannot distinguish blocking from spinning') and an explicit contraindication ('Do not use it when resuming the target is unsafe'). It also sets expectations that sampling perturbs scheduling and is not proof of progress.

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