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

Annotations only declare readOnyHint=true, and the description goes far beyond that: it reveals the compound nature of the endpoint, states that the result carries rendered palette downloads (PNG, PDF, ASE, JSON, CSS), and adds two hard behavioral rules — never present archive anchor colours as recommendations, and call palette_finalize when recommending a palette of your own. These are exactly the non-obvious traps an agent needs disclosed.

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 long but each sentence carries functional content — purpose, scope, alternative routing, param guidance, output contents, two caveats. Slight redundancy exists between 'returns a swatch URL' and 'carries the rendered palette and its ... downloads', and the palette_finalize sentence is a bit wordy, but for a compound endpoint of this complexity the density is justified.

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 an output schema present and readOny annotations covering safety, the description covers the essentials: full capability list, alternative routing, key param guidance, output artifacts, and two critical behavioral rules. The remaining gaps are minor but real for a tool with 8 optional params and no required ones — no precedence rule for image_url vs image_base64 when both are supplied, and no error/failure conditions.

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%, so baseline is 3. The description adds real meaning for style_contex ('pass style_contex for coherent archive matching e.g. English cottage garden, Victorian, MarsColour') and ties product_type to the cited catagories (textiles, interiors, fashion). For the remaining params (k, model, archive, image_url, grey_card_hex) it adds nothing beyond the schema, which limits it to a 4.

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 opens with a precise compound-endpoint statement ('one image in, full creative brief out') and enumerates the full pipeline: colour extraction, archive matching, scene understanding, style-period identification, product directions, prompt generation, and swatch URL. It explicitly names the siblings it replaces (palette_extract + palette_analyse + agent_brief), so an agent can distinguish it without inspecting other schemas.

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 an explicit alternative-and-condition: 'Use instead of chaining palette_extract + palette_analyse + agent_brief separately'. Also instructs when to pass style_contex for coherent archive matching and when to hand off to palette_finalize ('If you go on to choose a final palette OF YOUR OWN... call palette_finalize'), which routes the agent cleady.

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