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

Annotations already establish readOnlyHint=true, openWorldHint=true, and destructiveHint=false. The description adds some environmental context about CE running in a sandbox with no network, but it does not disclose what the tool returns, whether results are cached, or how availability is determined. For a read-only listing-style tool, the added behavioral value is minimal and the trailing ellipsis suggests missing information.

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?

The description is a single sentence that trails off with an ellipsis, so it is incomplete rather than concise. It spends its limited space describing the CE concept instead of front-loading the tool's action and return value.

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?

With no parameters and no output schema, the description must fully explain what the tool does and what an agent should expect back. It fails to do either, and the ellipsis indicates truncated content. The annotations cover safety but not the missing functional context.

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?

The tool has zero parameters, so there are no parameter semantics to explain. The baseline for a parameterless tool is 4; the description does not need to compensate for missing schema coverage.

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 explains what CE is and how it operates ('runs jobs on spare machines across ce-net, in a sandbox with no network'), but never states what the compute_backends tool itself does. It does not say whether the tool lists backends, selects an environment, or describes available compute capacity, so the agent cannot reliably distinguish it from compute_quote, compute_submit, or compute_status.

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?

There is no guidance on when to use compute_backends, when not to use it, or which sibling tool to prefer for related tasks. The only content is background about CE's operating model, not routing guidance.

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