art.provider.analyze

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

With no annotations provided, the description carries the full behavioral disclosure burden. It does disclose a genuinely useful trait: analysis runs locally without external APIs. However, it does not disclose potential side effects such as asset tagging via the asset_id parameter, error behavior when source_path does not exist or is not a PNG, or the performance/cost characteristics of the analysis.

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?

Two sentences with no filler; the core purpose is front-loaded and the behavioral differentiator (local, no external APIs) follows immediately. Both sentences earn their place. It only loses a point because it is efficient but slightly under-informative — a brief mention of the comparison operation would make it fully representative.

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?

With no output schema and no annotations, the description bears a heavy burden, and it falls short. It covers only three of the five operations (signature, clusters, palette) while omitting analyze_canvas and compare_canvases, says nothing about return values, and does not address side effects like asset tagging or how this tool differs from art.pipeline.analyze and art.canvas.analyze_ref. For a 6-parameter tool with 5 operation modes, this is incomplete.

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 100%, so the baseline is 3. The description's references to signature, clusters, and palette map onto three of the five operation enum values (compute_signature, detect_clusters, extract_palette), which lightly reinforces the schema. It adds no meaning about compare_path, connectivity, style, or asset_id beyond what the input schema already documents.

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 states a specific verb ('Analyze'), a concrete resource ('PNG file'), and a named provider ('canvas-analysis'), then enumerates the analysis categories (signature, clusters, palette). The 'without external APIs' phrase partially differentiates it from provider-execution siblings. However, it does not explicitly name any sibling (e.g., art.pipeline.analyze or art.canvas.analyze_ref) and omits the compare_canvases operation from its capability summary.

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?

'Runs local analysis... without external APIs' implies a selection criterion — prefer this tool when external API calls must be avoided — which gives some context. But no alternative tool is named and no when-not-to-use conditions are stated. Among near siblings like art.provider.execute, art.provider.operation, and art.pipeline.analyze, the agent is left to infer the boundaries on its own.

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