get_meminfo

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

No annotations are present, so the description carries the full behavioral burden. It discloses the return shape (parsed fields + raw text) and the output unit (kB), which is real added context, but says nothing about permissions, device/serial targeting, or failure modes for an adb-backed tool.

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 short clauses, front-loaded with the core action and the branch condition, then the return shape. No filler sentences.

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?

An output schema exists, so return values needn't be detailed, and the description correctly focuses on scope and units. However, with zero annotation coverage and an entirely undocumented 'serial' parameter, an agent still lacks enough to target the right device confidently.

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 coverage is 0%, so both parameters depend on the description. It explains what 'package' does (yields that app's total PSS in kB) but never mentions 'serial' at all, leaving device selection undocumented in both schema and description.

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?

States a specific verb+resource ('Return memory info') and immediately branches into the two scopes it serves: per-package PSS with a package arg, global Total/Free/Used/Lost RAM otherwise. An agent can distinguish it from siblings like get_top or list_processes from the description alone.

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?

The conditional behavior ('With a package... otherwise') impliedly tells the agent which argument selects which mode, which is usable context. But it never says when to prefer this over get_top, list_processes, or dumpsys meminfo, and offers no exclusions or prerequisites.

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