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

Adds real context beyond the annotations: it works without a live browser session, returns only a few thumbnails, and also reports whether live capture is available. It does not disclose whether a stale expected_rev causes a failure or a forced refresh, which is the one behavioral unknown for an otherwise read-only, idempotent tool.

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?

Three short sentences: scope first, the key negative disambiguation second, sibling routing last. No filler and the most important constraint is front-loaded.

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?

An output schema exists, so return values need no prose; annotations cover the safety profile (readOnly, idempotent, closed-world). For a read-only inspection tool the description supplies the missing pieces an agent needs: no browser required, output is thumbnails not a rendered screenshot, and where to go for live UI.

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 carries the full burden, yet it names no parameter. 'A few image thumbnails' only faintly hints at the node_ids maxItems of 4, and expected_rev, max_edge_px, and project_id scoping ('owned') are never explained. With four parameters fully undocumented in both schema and description, this is a substantive gap.

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 ('inspect') and resource ('real owned image thumbnails') plus a secondary signal ('whether live capture is available'), and explicitly negates the most likely misreading ('This is NOT a rendered Canvas screenshot'). It names the sibling tools it is not, so an agent can separate it from capture_view, view_session, and the inspect_* family without opening schemas.

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?

Provides explicit routing: 'For live UI use capture_view or view_session; for graph or media use inspect_layout/images/media,' and flags the precondition 'with no Canvas browser.' Both the when and the alternatives are named, leaving nothing to inference.

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