Get Human_Standard metadata (500-1200 tokens) + signed image URL for a museum artwork. ($0.10 / 1 GCX)
| Name | Required | Description | Default |
|---|---|---|---|
| artifact_id | Yes | Artifact ID from search results (e.g. 'met_437419') |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare read-only, idempotent, non-destructive behavior. The description adds value by specifying cost ($0.10/GCX), token range (500-1200), and 'signed' image URL, providing context beyond annotations.
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?
Single sentence with cost note, no wasted words, front-loaded with key information.
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 one parameter and no output schema, the description sufficiently explains output (metadata + signed URL) and cost. Minor gap: no explicit mention of output format (likely JSON), but inferable.
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?
Single parameter 'artifact_id' is fully described in the schema (including example). The description does not add additional parameter meaning beyond what the schema provides.
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?
Clearly states the tool retrieves Human_Standard metadata and a signed image URL for a museum artwork, distinguishing it from siblings like 'get_asset' and 'search_artworks' by specifying the resource type and output details.
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?
The description implies use for museum artwork retrieval with metadata and signed URL, but lacks explicit guidance on when to prefer this tool over similar siblings like 'get_asset' or 'get_artwork_oracle'.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets a distinct operation—artwork retrieval, image processing, asset management, watermarking, etc.—with clear descriptions that prevent confusion. Even similar tools like enrich_metadata and get_artwork_oracle are differentiated by depth and purpose.
Tool names follow a consistent verb_noun pattern in snake_case (e.g., get_artwork, remove_background, register_hash). The few non-verb-starting names (compliance_manifest) are standard and do not break the overall pattern.
27 tools is slightly above the typical range but justifiable given the broad domain covering artwork access, image processing, and digital rights. Each tool serves a unique purpose without redundancy.
The tool set covers the full lifecycle: search, retrieve, analyze, edit, save, and verify assets. Gaps are minimal—e.g., no metadata deletion tool—but the core workflows are fully supported, and the inclusion of compliance and provenance tools adds value.