device

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

Annotations already declare read-only, non-destructive, and closed-world, and the description's 'no install/uninstall' note reinforces that safety profile. It adds nothing about behavior the annotations don't cover: the side effects of logcat, how 'limit' caps the result, or what serial omission means for non-list actions.

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?

A single compact, front-loaded statement with no filler. The slash-delimited enumeration is dense but efficient; the only cost is that brevity shades into ambiguity around the enum mapping.

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 three parameters, 0% schema description coverage, and no output schema, the definition should be doing much more work. Key facts – which action requires serial, what each action returns, how limit interacts with logcat, and the distinction from the sibling 'packages' tool – are all missing.

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 description must carry the parameter burden and does not. It names some operation keywords but never explains 'action' semantics ('list' and 'inspect' are undefined), never says serial is required for non-list actions, and never explains what 'limit' (1-500) applies to.

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 the resource (ADB devices) and the operations: device listing, plus serial-scoped getprop/packages/processes/logcat. It also draws a boundary ('no install/uninstall'). However, the action names it lists don't cleanly map to the enum ('getprop' is not an enum value, and 'list'/'inspect' are never mentioned), so an agent must still guess which enum value corresponds to which described 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?

There is a real usage condition ('with explicit serial') and an explicit exclusion ('does not install/uninstall'), which is more than most definitions offer. But there is no routing guidance against the sibling tools – notably the sibling named 'packages' versus this tool's 'packages' action – leaving the most likely selection ambiguity unresolved.

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