Training Metrics

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

Annotations already declare readOnlyHint and idempotentHint, so safety is covered. The description adds genuinely useful behavior beyond that: cursor-based paging with a byte cursor and the 'start at zero' convention, plus the fact that it can be polled during a live run. It stops short of describing pagination termination or refresh/consistency behavior.

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 efficient sentence that front-loads the primary read action and appends the paging qualifier. Every clause earns its place, with no redundancy.

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 values need not be documented, and annotations cover the safety profile. The gap is parameter coverage: an opaque parameter like artifact_path is left undefined, and the relationship between cursor and limit paging is only half-specified.

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 0% across 4 parameters, so the description must carry the burden. It adds real meaning for 'cursor' (byte cursor, start at zero) but leaves 'run_id', 'limit', and especially 'artifact_path' entirely unexplained in both schema and 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?

States a clear verb and resource ('Read latest metrics') plus the paging capability and the context in which it applies ('while training runs'). It does not differentiate itself from the nearby sibling training_logs, which an agent could easily confuse with a metrics-reading tool.

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 phrase 'while training runs' implies the intended context for use, and the mention of paging implies the long-poll/streaming case. However, no alternatives are named (e.g., training_logs or training_get) and no when-not-to-use condition is given, so guidance remains implicit.

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