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

Annotations already declare this is a safe read (readOnlyHint=true, destructiveHint=false). The description adds real behavioral context beyond that: it names the return field referenceImageUrls and prescribes an unresolved-outcome path, which prevents hallucinated likenesses. Only the broader return shape is left unstated.

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?

Three short sentences, front-loaded with purpose then usage then failure handling. The parenthetical example earns its place by disambiguating the intent, and there is no filler.

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, the description usefully names referenceImageUrls and describes the fallback path, making it callable without further context. Minor gap: it does not say what happens when multiple characters or multiple photos match.

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 0%, so the description must carry the load. It does: 'name' is implicitly a person's name, and the optional case is covered by 'or the account's character', explaining behaviour when no name is supplied.

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?

States a specific verb and resource: resolve a person's saved character reference images within the account. It is distinct from generic image siblings like search_my_images or discover_brand_images, though it does not explicitly name those alternatives to route away from them.

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?

Explicitly says when to use ('when asked to include a named person') with a concrete example, defines the downstream step ('Pass the returned referenceImageUrls to create_image'), and gives fallback instructions when resolution fails ('ask which character or photo to use; never invent their likeness').

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