lm_runtime

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the mutation risk is broadly known. The description usefully differentiates actions by noting that check_updates is a dry run and that 'update' installs stable engines, and warns that inference must be retested afterwards — real added context. It still omits permission requirements, disruption scope, and download/size implications for a destructive open-world operation.

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 tightly packed sentences with the read/inspect path front-loaded before the mutating 'update' caveat. Minimal waste, though the phrasing is compressed to the point of slight ambiguity about which action maps to which verb.

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 single-parameter, multi-action tool with no output schema, the description covers the destructive path and its follow-up but does not explain what 'list', 'hardware', or 'available' return, nor the format of results. Adequate but with visible gaps given zero schema coverage.

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 0%, so the single 'action' enum is undocumented, and the description must compensate. It maps part of the enum ('inspect engines/hardware', 'check_updates', 'update') but leaves 'list' and 'available' undefined, so the enum is only partially disambiguated.

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 names verbs and resources for most actions ('Inspect engines/hardware', 'check stable updates', 'installs stable engines'), which is more than a tautology. However, two of the five enum values ('list', 'available') are never explained, and the description does not distinguish this tool from similarly-named siblings such as lm_status, lm_diagnose, or lm_models that plausibly also report engine/hardware state.

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?

'check stable updates (dry run)' implies that one action is safe to probe, and 'retest inference afterwards' gives an internal follow-up step. But there is no guidance on when to pick lm_runtime over lm_diagnose/lm_status, no prerequisites, and no when-not-to-use statement, leaving tool selection to inference.

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