skylight_import_events_from_photo

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

The description discloses critical behaviors beyond the destructiveHint annotation: it uploads to S3, the photo↔intent link is inferred from captured traffic rather than confirmed, the result is best-effort/unverified, and confirm:true is required to trigger side effects. This is far more than the annotation alone provides.

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?

The description is dense but every clause earns its place: purpose, safety gate, side-effect behavior, verification caveat, and follow-up workflow. It front-loads the core action and critical warning before procedural details.

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 no output schema and complex async side effects, the description is unusually complete. It states what the preview returns, when network calls occur, and exactly how to complete the import via sibling tools. Nothing essential for correct invocation is missing.

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?

With 75% schema coverage, the description still adds meaning by clarifying confirm's gating behavior, image_path's role as the absolute path used for the upload, and the dry-run preview. frameId is not addressed in the description, but the overall parameter semantics are substantially enriched by the behavior details.

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 description opens with a precise verb and resource: 'Import calendar events from a photo of a flyer/invite/schedule using Skylight's AI'. It clearly distinguishes this from sibling tools like skylight_upload_photo and the auto-creation polling/approval tools by naming the event_importer mechanism and the follow-up workflow.

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 explicit: without confirm:true it is a dry-run with no S3/network call; with confirm:true it uploads. It also names the exact polling and approval tools to use afterward, making the intended sequence unambiguous.

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