appium_diagnose

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

Annotations only declare readOnlyHint and openWorldHint; the description adds real behavioral context by stating it never retries and never changes state, and by enumerating what evidence it collects and that causes come with confidence scores. The main omission is the cost/latency profile, since reading logcat can be slow and is on by default.

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?

One dense but well-ordered sentence: purpose first, then the checks performed, then the outputs, then the read-only guarantee. Nothing is redundant, though the mid-sentence parenthetical list of screen conditions makes it slightly heavy to parse.

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, all-optional diagnostic tool with no output schema, the description adequately covers what the tool inspects and roughly what it returns (evidence, likely causes, next steps). It stops short of describing the shape of that evidence or how to act on confidence values, but the essentials for correct invocation are present.

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 100%, so every parameter is already documented, including the includeLogs default and the sessionId fallback to the active session. The description adds only indirect hints (it mentions logcat signals and screen/app state) and no new syntax or selection guidance, so baseline 3 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?

Names a specific verb-and-resource: it diagnoses a failure by checking session liveness, app state, screen state (dialog, keyboard, hidden/ambiguous/disabled target) and logcat crash/ANR/network signals, then returns evidence plus ranked causes and next steps. That is far more specific than the sibling tools (appium_screen_intel, appium_session_health, appium_observe), which each cover only one facet.

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 trigger is explicit and front-loaded: 'after a step fails'. An agent knows exactly when to reach for it. It does not, however, name how it relates to overlapping siblings such as appium_session_health or appium_screen_intel, so an agent cannot tell from this text whether diagnose subsumes them or should be paired with them.

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