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

Beyond the readOnly/idempotent annotations, the description discloses substantive behavior: older Web captures are converted with explicit gaps, measured bounds are not fixed sizing, and declared actions do not imply successful interactions. These are real interpretive caveats not derivable from structured fields. It stops short of describing output shape, but an output schema exists.

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-loads what is exported, then moves to consumption rules and caveats. The opening content list is dense but each clause names a distinct artifact section. A sentence or two of the interpretive guidance could be tightened without loss.

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 complex read-only export with a full output schema and rich parameter docs, the definition covers the missing pieces an agent needs: per-view calling, conversion gaps, evidence limitations, and the no-inference rules. Return-value detail is rightly deferred to the output schema.

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% and each parameter already documents its source (list_pages, list_versions, list_platforms) and disallowed values (no URLs, no OS names, no 'latest' alias). The description reinforces per-view and version-pinning intent but adds no new syntax or format details beyond the schema, so the 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?

Opens with a specific verb ('Export') and resource ('platform-neutral reconstruct.scene.v1 interface') and enumerates exactly what the artifact contains (profiles, frames, node hierarchy, layout constraints, transitions, motion). An agent can distinguish this composite scene export from narrower siblings like get_page_artifacts, get_page_stack, or get_scenario_scene.

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 concrete usage conditions ('Consume the JSON programmatically', 'Request each saved view separately', 'Native captures require a published scene; do not invent them') and exclusions about interpreting results. It does not explicitly name which sibling to prefer when a caller wants only components or styles, so routing to alternatives is left implicit.

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