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

Discloses behavior well beyond the annotations: it sends a command, waits ~5s for a new frame, defines the `fresh` flag semantics, and specifies fallbacks for slow/offline screens (last stored frame, fresh:false) and oversized frames (>2 MB no inline image). It also states the required `screen.edit` permission. This is consistent with readOnlyHint=false, since a command is dispatched to the player.

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 action and its output, then progressively layers timeout, return fields, and fallbacks. Dense but every sentence carries distinct operational information; the return-field enumeration is slightly redundant given an output schema exists.

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?

Covers everything an agent needs: the permission requirement, the wait/timeout, the freshness semantics, and the degraded-path behavior for offline or oversized frames. An output schema exists, so the additional return-field detail is bonus rather than a gap.

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 100% and the schema already documents screenId with an example and a pointer to search_screens. The description only adds the constraint 'One screen per call,' which the schema already implies via a single required screenId, 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?

States a specific verb and resource ('Take a screenshot of one screen now and return it as an image') with explicit scope ('one screen'). It also distinguishes its role from the diagnostic sibling by directing agents to screen_health for 'WHY' questions.

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 a clear purpose ('to check what is actually on the panel') and names screen_health as the alternative for a related-but-different question. It does not, however, address when to use this versus other screen-state siblings like refresh_screen.

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