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

Annotations indicate idempotentHint=true (safe to retry) and destructiveHint=false (not destructive). The description adds value by naming the underlying library (ExifTool), detailing the two modes, mentioning the dependency on 'enrich_metadata' for the full_gcx mode, and disclosing the cost. There is no contradiction with annotations. The description provides behavioral context beyond what annotations alone convey.

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?

The description is concise (two sentences) and front-loaded with the main action. It efficiently conveys purpose, modes, and cost without extraneous information. While it could benefit from a slightly more structured presentation (e.g., bullet points for modes), it remains clear and to the point.

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?

Given the tool's complexity (3 parameters, nested object, two modes, cost, external tool dependency), the description covers the essential aspects: what the tool does, its modes, the required input format, and cost. It also references the associated tool 'enrich_metadata' for the full_gcx mode. There is no output schema, but the description does not need to explain return values. It is adequately complete for an agent to use the tool correctly.

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?

The input schema has 100% description coverage, so the baseline is 3. The description adds meaningful semantics: it explains that 'metadata' for full_gcx should be the output of 'enrich_metadata', and it lists the fields included in each mode. This helps the agent understand the expected structure beyond the schema's enums and types.

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 clearly states the tool's function: 'Embed metadata into image via ExifTool.' It specifies two distinct modes ('standard' and 'full_gcx') with clear field lists, differentiating it from siblings like 'enrich_metadata' which prepares metadata, or 'watermark_embed' which embeds watermarks. The verb 'infuse' combined with resource 'metadata' and the explanation of modes makes the purpose highly specific.

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 explains the two modes and when each is appropriate: standard for limited XMP/IPTC fields, full_gcx for the complete Golden Codex namespace. It also notes the default mode and references the cost per use. However, it does not explicitly state when NOT to use this tool, such as for non-image files or when no external tool is available. Overall, the guidance is clear but could be more comprehensive.

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