props

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

With no annotations, the description carries the behavioral burden and does disclose the important traits: privilege requirements per property prefix, routing of persist.waydroid.* through `waydroid prop set` versus setprop, and the delayed-effect caveat that most Waydroid settings only apply after a session restart. It leaves gaps around error behavior for unknown property names and whether prior values are recoverable after a set.

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?

Four compact sentences, front-loaded with the resource and then ordered by action, with no filler. The telegraphic style ('`get` reads names or a regex') is efficient but slightly terse; nothing is wasted, though a lead-in fragment rather than a full sentence costs a little readability.

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 five-parameter, no-annotation, no-output-schema tool, this covers the essentials: all three actions, the root constraints, and the restart side effect. Return-shape details (e.g., what `get` yields for a missing property, how multiple names are returned) are absent, which is a real but modest gap given no output schema exists.

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 80%, so the schema already documents names, name, value, action, and pattern. The description adds moderate value by mapping actions to parameters ('get reads names or a regex', 'set changes one', reinforcing single-property scope despite the plural `names` array existing), but does not explain the alternation between `names` and `pattern` or what happens when both are supplied.

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 ('Android system properties') and breaks the tool into three concrete sub-actions: `waydroid` lists persist.waydroid.* settings with meaning and value, `get` reads names or a regex, `set` changes one property. This is far more specific than the terse name 'props' suggests, but it never contrasts itself with a sibling such as `shell`, which could also read/write properties.

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?

Each action carries its own usage context: `waydroid` for a curated listing, `get` for names or a regex, `set` for a single property. It also flags when a set requires root (only debug.*, log.tag.*, persist.log.tag.* work without root) and that changes need a session restart, which tells the agent when this tool is the right entry point. It stops short of any explicit exclusion or alternative-selection rule.

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