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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so safety needs no restating. The one piece of behavior the description could own — what "kept" means, whether results are filtered or paginated, what a machine entry contains — is absent.

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 words with nothing extraneous, but the terseness comes at the cost of meaning rather than from efficient phrasing. The key term "kept" is never grounded.

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 is the only place an agent can learn what comes back and what "kept" filters out. It leaves both unanswered, so the definition is under-specified for even a simple list tool.

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 takes no parameters, so there is nothing for the description to clarify beyond the schema. Baseline of 4 applies.

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?

"List kept computers" gives a verb and a noun, but the noun diverges from the tool name and its machine_* siblings, and "kept" is unexplained jargon. An agent cannot tell from this whether it returns all machines, only retained ones, or how it differs from machine_get or machine_health.

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 statement of when to use this versus machine_get, machine_health, or the machine_* mutators. Usage is only implied by the word "List".

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