screenstudio_desktop_perform

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

Annotations already declare readOnlyHint=false, openWorldHint=true and destructiveHint=true, so the safety profile is covered; the description adds context they cannot, namely per-action hold defaults (click 1.2s, type 0.9s, key 1s, scroll 1.2s), that the whole run is one continuous take, how markers alter the recording, and how minDurationMs stretches the final hold. It does not warn that this drives the real cursor/desktop or mention auth/failure behavior, so not a 5.

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 the core action, then layered with detail; there is little filler since nearly every clause carries a default, a threshold or an integration rule. It is somewhat dense and parenthetical-heavy, which slightly hurts scannability, but nothing is redundant.

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 5-parameter, 0%-coverage, no-output-schema tool whose annotations already cover safety, this is adequate but not complete: the required observationToken's origin and lifetime are unexplained, most step action types and their parameters get no treatment, and nothing is said about what the call returns or how failures mid-take behave.

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 compensate and largely does: pace, markers and minDurationMs all get concrete semantics and defaults beyond the raw schema, and steps gets a behavioral contract (max 12, hold after each). Gaps remain — observationToken (a required parameter) is never explained, and holdMs plus several action types (drag, taps, hold, focus, doubleClick, move) are undocumented.

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 and resource — 'Perform a whole beat in one take while recording' — with concrete scope (up to 12 steps, each followed by a visible hold). An agent can tell this is the multi-step, recorded desktop-automation sibling, though it never explicitly names screenstudio_desktop_action as the single-step alternative, so the differentiation is implied rather than stated.

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?

Gives real usage context: one continuous take yields natural pacing, pace 1.3 is calmer, markers:true is what pairs the beat with screenstudio_analyze and screenstudio_narrate (pinToMarkers), and minDurationMs is meant to be set from a narration line's durationMs plus ~400ms. There is no explicit 'do not use this when…' or a named alternative for single actions, so it stops short of a 5.

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