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

With no annotations, the description carries the full behavioral burden. Saying 'Read-only' is a helpful and explicit safety signal that prevents mutation assumptions. However, it does not disclose ordering, result limits, retention windows, or what 'recent' means, leaving some ambiguity.

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 that front-load the resource, then list returned fields)Skip ahead. No filler or redundant repetition of schema details. Every word contributes meaning.

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 low-complexity read-only listing tool with two fully documented required parameterscars, the description is nearly complete. It states resource scope, output content, and read-only behavior. The main gap is no explicit pagination or recency window, but this is minor for such a simple call.

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%, with slug and computeApiKey both documented. The description adds little beyond the schema, though 'one of your processors' reinforces ownership scope and the read-only note aligns with the API key's read scopes. 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 identifies a specific resource: recent runs of one processor, with clear output content (status, cost, duration). This distinguishes it from siblings like cloud_list_processors and cloud_get_training_run. It lacks an explicit verb like 'list' or 'get', but the noun phrase 'Recent runs' sufficiently communicates the operation.

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?

No explicit guidance on when to use this tool versus alternatives. Sibling comparison implies it is the go-to for processor run history, but the description does not mention exclusions or direct alternatives. An agent must infer timing or selection criteria from the name.

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