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

With readOnlyHint and idempotentHint already in annotations, the description carries the lower safety burden but adds substantial behavioral context: the default includeBuildConfig=true behavior, the conditional presence of preset.paletteValues (included only for non-unmodified built-in palettes, absent entirely otherwise, never partial), and the empty-build-plus-warning edge case. It tells an agent exactly what the response will contain and what an absent paletteValues field means, which annotations and schema cannot convey.

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 long and dense - a single multi-clause paragraph that is harder to parse than it needs to be - but every sentence carries load-bearing information: core read behavior, adaptation workflow, palette semantics, sibling routing, and return shape. There is minor redundancy (the riddle_template_use recommendation appears twice) and bullet formatting would improve scannability, but the most important facts are front-loaded in the first sentence.

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?

With no output schema, the description correctly takes on the return-value burden, specifying the full field list and the empty-build warning edge case. The tricky palette semantics - built-in versus custom palettes, how colors and fonts resolve via riddle://reference/palette/built-in-palettes matched by name - are fully specified. Given the tool's complexity and its chaining role in an adaptation workflow, nothing essential 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 description coverage is 100%, so the baseline 3 applies: id, omittedDefaults, and includeBuildConfig all already carry detailed descriptions with types, defaults, and purpose. The description adds minimal parameter-level value - it reinforces that includeBuildConfig true is 'the point of this tool' and provides workflow context about passing this id as templateId, but it largely restates what the schema's own parameter descriptions already say.

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 sentence names the exact operation - reading one template - and the distinguishing default of including its build configuration, linking it to the build shapes of riddle_get and riddle_builder_create. It also separates itself from siblings by framing the tool as adaptation ('ADAPTED rather than copied') and contrasting it with riddle_template_use, which copies the template whole. The generic title 'Get riddle template' is fully compensated by the specific first sentence.

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 explicit when-to-use guidance: use this tool to adapt a template by editing the returned build and rebuilding with riddle_builder_create, and 'Not changing anything? riddle_template_use is one call and copies the template whole' states the exact alternative condition. It even routes the edge case - templates with no build-configuration equivalent - back to riddle_template_use, and explains when includeBuildConfig=false is appropriate. There is no ambiguity about when to pick this tool over its siblings.

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