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

With no annotations, the description carries the full burden and does well: it discloses the two palette variants checked, the exact thresholds, that failing pairs list slots to adjust, and that contrast never blocks publishing. It does not explicitly state it is read-only, but 'Audit' and 'Advisory' imply no mutation.

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?

Three front-loaded sentences carry purpose, input, thresholds, and advisory behavior with no filler. Every sentence earns its place.

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 tool has only two parameters, an output schema exists, and the description supplies thresholds, input alternatives, palette variants, and follow-up guidance via set_palette. Nothing needed to invoke it correctly is missing.

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% and the schema already documents the exactly-one-of style_id/theme rule and theme format. The description adds only a concise restatement and a pointer to create_style, which is useful but not a major increment over the schema.

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 specific verb ('Audit'), a precise resource ('a map style's colour contrast'), and an explicit standard (WCAG 2.1 thresholds for label text and graphics). This clearly distinguishes it from sibling tools like check_adr_tunnel or set_palette.

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?

It gives a clear invocation condition ('Pass a hosted style_id OR an inline theme document') and directs failed pairs to set_palette. It lacks an explicit 'when not to use' contrast, but the advisory note that publishing is never blocked on contrast conveys the appropriate context.

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