list_runs

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

With no annotations, the description must carry the behavioral load, and it does disclose useful semantics: the return fields and the meaning of each status ('finished' has final metrics, 'no_eval' does not). It omits the read-only assumption, ordering, pagination and any permission requirements, so the transitive behavior is only partially covered.

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 short sentences, each earning its place: the first declares content and field semantics, the second declares the call-order guidance. It is front-loaded with the purpose and wastes nothing.

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 purpose, returned fields, status semantics and call-order advice. Ordering and pagination are unstated, but otherwise an agent has what it needs to invoke it correctly.

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?

There is only one parameter and the schema describes it fully ('Only list runs of this scene, e.g. lego'), so the baseline is 3. The description adds no filtering syntax or default behavior beyond what the schema already states.

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?

It states a concrete verb (list) and resource (training runs) and names the fields the listing exposes (scene, planned iterations, status), which an agent can act on without opening the schema. It never names the sibling get_* tools it is meant to precede, so differentiation is implied rather than explicit.

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?

'Call this first if you don't know the run names' gives a clear entry-point condition that separates discovery from the follow-up tools like get_run_config or get_final_metrics. It doesn't state when not to use it or name alternatives explicitly, so it falls short of a 5.

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