review_quality

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

With no annotations, the description carries the full burden and does disclose meaningful behavior: a two-repair limit, the <=0.5m threshold gating auto_fix, the explicit absence of an aesthetic score, and that repair_quality auto-refreshes the comparison. Gaps remain around permissions, what state is mutated/consumed, and the async polling contract details.

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?

It is front-loaded with the core purpose and every sentence adds distinct information (threshold, vision dependency, limit, polling). The prose is dense and jumps between concerns, but there is little filler, so the size is defensible for the behavioral content conveyed.

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 annotations, no output schema, and 0% schema-description coverage, the description covers workflow and behavioral limits well but leaves parameter meanings (preset, asset_id) unexplained and gives no expectation of the returned findings structure. Adequate but with clear gaps given the complexity.

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 must compensate for all three parameters. It explains auto_fix's semantics reasonably (alignment to a collision surface when gap <=0.5m) but says nothing about asset_id or the preset parameter (e.g., what values beyond the default 'scene_prop' mean), leaving most parameters undocumented.

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 opening line states a verb-plus-resource ('Measure native issues and capture same-camera before/after with a two-repair limit'), which signals a quality-review tool, but 'native issues' is vague jargon and the phrase never crisply says what the tool produces. It is distinguishable from get_review and repair_quality only by inference, not by an explicit contrast.

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?

It gives real conditional guidance: auto_fix only aligns when the measured gap is <=0.5m, visual findings require get_preview/get_art_reference, and polling is done via get_task_status. It also implies repair_quality is the sibling that applies edits, so routing is largely covered even without an explicit 'do not use when' clause.

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