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

Annotations only declare readOnlyHint=true, so the description carries the behavioral burden. It discloses several notable behaviors: the result carries rendered palette and multiple download formats, the tool performs cultural naming and style period identification, and it warns about presenting archive anchors as recommendations. It does not fully describe error behaviors or output schema internals, but the key behavioral traits are transparently stated.

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 dense but each sentence carries real operational meaning, and the most important routing guidance ('Use instead of chaining...') appears early. It is longer than a minimal sentence, but the compound nature of the endpoint and the multiple behavioral warnings justify the length. Slight room for trimming in the trailing instructions, but still well-structured.

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, the description does not need to enumerate return fields in detail, and it effectively covers the core workflow, intended use, customer-facing outputs, and a critical follow-up action. It leaves out exact response shape, but the output schema covers that. Given the tool's high complexity (8 optional parameters, compound pipeline), the description is complete enough for an agent to select and invoke it 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?

Schema description coverage is 100%, so the baseline is 3. The description adds extra meaning beyond the schema by explaining how style_context is used ('Restricts archive matching to coherent cultural set') and by giving concrete examples for the parameter ('English cottage garden', 'Victorian', 'MarsColour'). It also clarifies the role of the image inputs implicitly through 'one image in'. This justifies a slightly above-baseline score.

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 states a clear compound action: one image in, full creative brief out, listing concrete extraction and generation steps. It also distinguishes itself from an explicit alternative (chaining palette_extract + palette_analyse + agent_brief separately), so an agent can identify exactly what this endpoint does.

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 explicitly tells when to use this tool ('Use instead of chaining palette_extract + palette_analyse + agent_brief separately'), when to pass style_context, and what to do with the result ('show them to the customer'). It also provides negative guidance ('Never present the archive anchors...') and a follow-up action condition ('call palette_finalize once if you choose a final palette of your own'). This is strong, actionable usage guidance.

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