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

Annotations already declare the mutation profile (readOnly=false, idempotent=false, destructive=false). The description adds a real workflow prerequisite (prior read_image) and a caution against using it as a vision substitute. It does not say whether images append to or replace content in targetDocName, nor what happens when the doc already exists — a meaningful gap for a non-idempotent write.

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 compact sentences that front-load what the tool does before the usage caveat. No filler. The phrase 'labeled the photos in the system prompt' is slightly terse but still parseable.

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?

A 5-parameter mutation tool with no output schema and zero schema descriptions leaves the description carrying too much. An agent still cannot tell the image payload format, the 30-item cap, or the create-vs-update semantics of targetDocName from this text.

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, and it only clarifies autoCaption. Four parameters are unaddressed: what agentId scopes, that images items carry data/mimeType/sourceUrl and are capped at 30, and critically whether targetDocName refers to an existing doc or one to be created.

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+resource: 'Upload images into the agent KB'. It is clearly distinguishable from create_kb_doc, bulk_create_kb_docs, and patch_kb_doc because it targets images specifically. No sibling is named, but the resource is narrow enough that confusion is unlikely.

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?

Gives explicit ordering and a negative condition: call read_image first, label the photos in the system prompt, then use this as a backup — 'not a substitute for looking at them'. It doesn't say when to prefer this over create_kb_doc or bulk_create_kb_docs for mixed content, but the primary pitfall is addressed.

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