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

The readOnlyHint annotation already signals safety, and the description adds substantial behavioral context beyond that: it is a compound tool that returns rendered palettes with PNG/PDF/ASE/JSON/CSS downloads, it warns against presenting archive anchors as the recommended colours, and it instructs the agent to call palette_finalize for any independently chosen palette. This is rich, non-obvious behavioral disclosure that annotations alone would not provide.

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?

Every sentence earns its place: the compound-tool framing is front-loaded, the replacement chain is explicit, the usage boundary is clear, and the output/presentation warnings are operationally important. Despite its length, there is no filler; each clause carries routing, safety, or workflow information an agent needs.

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?

For a compound tool with 7 parameters and an output schema, the description is complete: it covers what the tool returns, when to use it, when not to, how it differs from siblings, and how to hand off to palette_finalize. The output schema exists, so the absence of a detailed return-value list is not a gap. The readOnlyHint annotation covers the safety profile.

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 the baseline is 3; the schema already documents concept, medium, avoid, n_colours, and the include_* flags. The description maps some high-level inputs ('concept, medium, ... constraints') to the schema, but it also mentions 'audience,' which is not an actual input parameter. That minor mismatch prevents extra credit beyond the schema-backed baseline.

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 uses a specific verb+resource framing: 'One-call compound tool' that 'receive[s] a complete design package' from a concept. It explicitly names the sibling tools it replaces, distinguishing it from query_conceptual, palette_from_concept, colour_story, and others, so an agent can immediately tell this is the aggregator tool rather than any individual step.

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 states the exact use case ('when an AI agent or user needs a complete, deployable colour direction in a single call') and explicitly says what it is not for ('Not for iterative refinement — use individual tools for that'). It also gives follow-up guidance about calling palette_finalize when the agent chooses its own palette, which is actionable and specific.

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