ue5_screenshot

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

With no annotations, the description carries the full burden and does well: it discloses the return payload (image block + saved_path / camera_used provenance), a side effect (PNG saved for the dashboard), and failure behavior (fail-loud when PIE is not running). It doesn't state cost, latency, or whether capture disturbs editor state, leaving a small gap.

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 and workflow, then source semantics, then return values — a sensible ordering with no filler sentences. The piped, telegraphic phrasing and the duplicated bilingual tail make it denser than ideal but nothing is wasted.

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 tool with a nested camera object and no output schema, the description covers sources, return shape, provenance, and the fail-loud precondition — enough for correct invocation. The 768px default and the Pillow dependency for annotate are handled by the schema, so the remaining omission is minor.

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 camera-required-for-agent_camera constraint. The description restates those same facts rather than adding new meaning (e.g. valid pitch/yaw/roll ranges or how annotate interacts with Pillow availability), so it sits at the baseline.

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+resource ('Screenshot for visual self-check') and enumerates the three capture sources with their semantics, so an agent can tell exactly what it gets. No sibling tool in the list overlaps with screenshotting, so differentiation is implicit but unambiguous.

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 'edit -> screenshot -> inspect -> fix' workflow gives concrete usage context, and preconditions are named per source ('pie (fails loudly if PIE not running)', camera required for agent_camera). It stops short of saying when *not* to use it or pointing to a sibling alternative, so it doesn't reach a 5.

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