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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds real behavioral context beyond the annotations: that the snapshot is 'live' and that after completion it 'carries the recorded upload,' which tells the agent the object's payload changes with session state.

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 tight sentences: the resource and its returned fields are front-loaded, followed by the completion/follow-up behavior. No wasted phrasing.

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?

Output schema exists, so return values need not be spelled out; the description covers purpose, state contents, and the follow-up action. Nothing an agent needs to invoke it correctly is missing.

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?

Single parameter with 100% schema description coverage; the schema already explains execution_id including its origin (from calibration.start). The description adds no syntax or format detail beyond that, so the baseline 3 applies.

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 resource and action ('Live snapshot of a calibration session') and enumerates what it exposes (phase, current trial, progress, paused), so the agent knows exactly what this returns. It is clearly the read/status member of the calibration.* family, distinct from pause/resume/start/train.

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?

Provides clear forward context: 'Once complete... call calibration.train to turn it into the subject's own classifier,' which routes the agent to the correct next tool. It stops short of stating when to use this vs other status-like siblings (e.g., stream.status, execution.get), so no explicit exclusions.

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