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

With no annotations, the description's 'Read-only' is the primary side-effect disclosure and is genuinely informative. It also states exactly which data is returned, though it could add error or authorization context; the computeApiKey parameter description partially covers authorization outside the main description.

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 short, front-loaded sentence conveys purpose, scope, return contents, and safety in eleven words. Every component 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 simple two-parameter read-only lookup with a fully documented schema and no output schema, the description covers what the tool does, the scope (single run by id), the key returned fields, and side-effect safety. No decision-critical information 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?

Schema description coverage is 100%: runId is documented as a UUID and computeApiKey has source/scope instructions. The description adds no parameter-level detail, matching the baseline for fully self-documented schemas.

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?

Clearly identifies a singular training run lookup by id and names the fields returned (status, progress, billed hours), so it stands apart from sibling list_training_runs and other cloud_get_* tools.

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?

'One ... by id' signals the tool is for a single existing run rather than listing, and 'Read-only' tells the agent this is a safe inspection call. However, it does not explicitly name alternatives or state when not to use it, so it stops short of a perfect 5.

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