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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered by structured data. The description adds genuinely useful scope detail — it validates in both light and dark modes and covers contrast for brand colors as well as text and state — but says nothing about what a validation run produces (error list, boolean, thrown exception) or whether partial failures are tolerated.

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?

A single front-loaded sentence that names the resource first, then the contract, then the individual checks. No filler or repetition; the density of the check list is justified by the tool's purpose, though the trailing 'no claro e no escuro' slightly lengthens an already packed clause.

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?

There is no output schema, so the description should explain what validation returns — a list of violations, a pass/fail flag, or thrown errors — and it does not. For a read-only checker with a nested, undocumented input object, the definition is adequate about what is checked but silent on both input shape and result shape.

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?

With only one parameter at 0% schema description coverage and a bare `{"type":"object"}` definition, the description carries real weight by identifying the argument as a 'ThemeProvider object' rather than an arbitrary object. However, it does not describe the expected shape of that nested theme object (token structure, where label lives, how references are expressed), so an agent still cannot construct a valid input from the description alone.

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?

States a specific verb ('Confere') and resource ('um tema'), and enumerates the exact checks performed: recognized tokens, label, resolvable references, and AA contrast across text/state/brand in light and dark. This is far more specific than the name alone, though it never explicitly contrasts itself with the sibling refy_validate, leaving the generic-vs-theme-specific split to inference.

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 framing 'contra o contrato dos temas do Refy' implies this is a pre-flight check on a ThemeProvider object, but there is no explicit when-to-use statement, no mention of when to prefer refy_validate, and no guidance on what to do with failures. Usage is inferable rather than stated.

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