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

The description goes well beyond the readOnlyHint annotation, disclosing palette-level deduplication, low-confidence alternatives, the rendered palette with downloadable formats, and a critical guardrail: never present archive anchors as recommended colours. This gives the agent a clear behavioral model of the tool's outputs and constraints.

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 every sentence earns its place: core function, output details, workflow placement, download handling, guardrails, and finalization handoff. It is front-loaded with the primary purpose and structured so the agent can quickly extract the key behavior.

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?

The description fully equips the agent to call the tool correctly: it explains the input provenance, output structure, deduplication behavior, downloadable artifacts, and post-call actions. Even without reading the output schema, an agent would know what to expect and how to use the result in the customer-facing workflow.

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 schema already documents all parameters. The description adds context for 'n' by mentioning alternatives when confidence is low, but it does not add significant meaning beyond the schema's own descriptions. This is the expected baseline when the schema fully covers parameters.

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 ('Analyse') and resource ('Colour Memory archive'), and specifies the exact output: nearest named archive entry with cultural name, source, claim_strength, do_not_say guardrails, and alternatives. This clearly distinguishes it from siblings like archive_search or palette_compare by focusing on analysis and recommendation evidence.

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 when to use the tool: 'Use after extracting colours from a photo or generating a palette.' It also gives a clear workflow boundary by telling the agent to call palette_finalize if it later chooses a final palette. It does not explicitly name sibling alternatives to exclude, but the contextual instructions are strong.

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