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

The description discloses that the tool returns 'not enabled' when training is off on Cloud, which is a useful behavioral trait beyond what annotations provide (no annotations exist). It also explicitly states 'Read-only', which is valuable since no readOnlyHint annotation is present. It doesn't mention pagination or output format, but the key behavioral quirk is disclosed.

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 short sentences with no wasted words. The core purpose is front-loaded, the behavioral quirk is stated, and the read-only nature is appended. 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 simple one-parameter list tool with no output schema, the description covers the essential context: what it lists, the key required, the 'not enabled' edge case, and read-only safety. It could mention whether it returns all runs or only recent ones, but given the simplicity, it's nearly complete.

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 the computeApiKey parameter well, including where to find it and that read scopes suffice. The description adds no additional parameter-level detail beyond the schema, so baseline 3 is appropriate.

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 clearly states the tool lists LLM training runs for a wallet behind a compute API key, which is a specific verb+resource combination. It distinguishes itself from cloud_get_training_run (singular) and other cloud_* list tools, though it doesn't explicitly name a sibling.

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 implies usage context: it's for listing training runs when training is enabled, and mentions the 'not enabled' response when training is off. However, it doesn't explicitly state when to prefer this over cloud_get_training_run or other list tools, nor does it provide exclusions.

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