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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds a genuinely non-obvious behavioral trait beyond that: the default response is trimmed, and the parameters state exactly which fields the trimmed view contains and when to opt into the full object.

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, front-loaded with the core purpose, followed immediately by the default-vs-full behavior. Every clause earns its place with no repetition of the name or title.

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?

An output schema exists so return structure need not be explained, and annotations cover the safety profile. The description supplies the one thing structured fields cannot: the trimmed-by-default behavior and the field list of the default view, making it sufficient for correct invocation.

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 coverage is 100%, so the baseline is 3, but the description goes beyond the schema by explaining what the default (full=false) actually yields — the trimmed field list — which the schema does not document. It thus characterizes the negative case of a boolean flag rather than merely repeating its description.

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 names the specific resource (metrics) and scopes it to a completed run, and even enumerates the default payload fields (accuracy, kappa, ITR, confusion matrix, per-class). It is clear what the tool returns, though it does not explicitly contrast itself with the nearby execution.get or execution.artifacts siblings.

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 description implicitly guides the agent on the default vs. detailed retrieval mode ("Trimmed by default... full=True returns the complete result object"), which is useful. However, it gives no explicit when-to-use guidance relative to alternatives such as execution.get, nor any prerequisites (e.g., that the run must have finished).

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