act

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

With no annotations, the description carries the full behavioral burden and does so well: sequential execution with stop-at-first-error, targets judged against the screen re-read immediately before the gesture, non-ASCII text routed through the clipboard, confirm gating requiring an explicit user "yes", and a result legend (✓ verified / ~ sent-unverified / ✗ failed-or-refused). This is substantive disclosure an agent cannot get from the schema.

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?

Front-loaded with purpose in sentence one, then a dense semicolon-delimited catalogue where nearly every clause carries new information, closed by a concrete compound example. It is long but not padded; the compression into one paragraph makes it slightly harder to scan than a bulleted form would be.

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 tool with 10 gesture types and 10 step fields, no annotations and no output schema, the description covers execution order, error behavior, target resolution, confirmation gating, and the shape of the result. Return-value detail is thin ("l'écran à jour" plus the ✓/~/✗ legend) and preconditions such as device unlocked state are unaddressed, so a small gap remains.

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?

Though the reporting signal puts schema coverage at 0%, the description compensates with real semantics: the "[N]" bracket convention and the rule that a bare number is treated as literal text (not an index), target formats "x,y"/visible text, per-gesture field mapping (direction = content direction, gone for wait, keys incl. ctrl+a), and the confirm requirement for enter/KEYCODE_*. It leaves amount and timeout uncovered, so not a full 5.

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 opening sentence states a specific verb+resource: it executes gestures on the phone in order, stopping at the first error, then returns the refreshed screen. That is far more precise than a tautology and clearly marks it as the action counterpart to the read-only siblings (e.g. "look"), but no sibling is named, so differentiation is left implicit.

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?

Usage is implied through the gesture vocabulary and per-step field rules (e.g. confirm=true for enter/KEYCODE_*), but there is no explicit when-to-use / when-not-to-use statement and no mention of alternatives such as "look" for observation or "launch" for starting apps. The agent must infer the boundary from the semantics.

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