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

Annotations declare readOnlyHint=true, so the safety profile is already known. The description adds valuable context: ephemerality (5-minute expiry), the return of image_id, and downstream usage patterns. This is meaningful behavioral context beyond what annotations provide, though it doesn't address potential failure modes or rate limits.

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 efficient sentences with zero waste. Each sentence adds distinct value: what it does, what it returns and its validity, and when to use it. The size threshold heuristic is compact and actionable.

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?

Tool has 3 optional params, nested objects, and an output schema — moderate complexity. The description covers the purpose, output, validity window, downstream consumers, and size guidance. It doesn't document edge cases (what happens on invalid image, error responses), but the ephemeral design is simple enough that this is acceptable. The 'unlike palette_extract' contrast adds helpful cross-tool context.

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 100%, establishing baseline 3. The description adds value by clarifying the image_base64 parameter is for locally uploaded files with no public URL, and notes 'No size limit here (unlike palette_extract)' — a cross-tool contrast that helps disambiguate. The ephemeral processing context also clarifies why ingestion matters.

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?

Description uses a specific verb+resource ('Upload an image to Colour Memory') and clearly states the output (ephemeral image_id valid 5 minutes). It also names downstream consumers (palette_extract, image_brief), distinguishing this as an ingest step from the many sibling analysis tools.

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 gives clear context on lifecycle ('valid 5 minutes') and references downstream tools by name, but doesn't explicitly state when NOT to use it or name specific alternatives. The 'use for any image over 50 KB' hint gives size-based guidance, though the alternative path for smaller images isn't stated.

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