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

Beyond annotations, the description discloses determinism, zero LLM cost, that the result carries downloadable PNG/PDF/ASE/JSON/CSS artifacts that should be shown to the customer, and a critical anti-pattern warning: 'Never present the archive anchors a colour was derived from as the colours you are recommending.' This is exactly the kind of behavioral gotcha disclosure that prevents misuse, and it is consistent with readOnlyHint being true.

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?

Four dense sentences with zero filler: purpose, output inventory, determinism/cost, artifact-handling instruction, a behavioral warning, and a routing instruction. Every clause earns its place, and the most decision-relevant facts (breadth, determinism, cost) are front-loaded before the caveats.

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 tool with five parameters, one required, plus an output schema, the description covers the full surface an agent needs: what is returned, which artifacts to surface to the customer, the evidence-vs-recommendation distinction, and the follow-up call to palette_finalize. The only omission — how parameters influence the output — is minor given 100% schema coverage and the existing output schema.

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 schema already documents all five parameters and their defaults. The description adds no parameter-level meaning beyond the schema — it explains outputs and workflow but not how market, medium, use_case, or brand_category shape the result. This is the baseline 3 given full schema coverage.

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 opening phrase 'Complete brand colour system in one call' names a specific verb and deliverable, and the detailed output list (colour roles, light/dark role maps, typography guidance, usage rules, design tokens, citation cards) makes it unmistakable what this tool produces. The 'in one call' framing and the breadth of outputs clearly distinguish it from narrower siblings like palette_generate, colour_strategy, or brand_guideline_pdf.

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 for when to invoke this tool (when the full brand system is wanted 'in one call') and explicitly routes a downstream scenario: 'If you go on to choose a final palette OF YOUR OWN from this evidence, call palette_finalize once with those exact colours.' However, it does not state when-not-to-use it or name simpler alternatives for partial needs, so it stops short of a full 5.

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