Liquid Composer

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

Annotations already declare readOnlyHint=true and openWorldHint=false, but the description adds genuinely useful behavior: the recipe is carried in the URL fragment, so nothing is sent to a server on open. That privacy/transport trait is not derivable from annotations or schema.

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 short sentences, front-loaded with the action and outcome, followed by the two facts an agent needs (no server transmission, image source restriction). No filler.

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 deeply self-documented schema carries most of the load and there is no output schema, so the description needn't explain the recipe shape. It could state the return form explicitly (e.g. that a URL string is returned) rather than only 'a link', which is the one small ambiguity.

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?

Top-level coverage is 0%, but nested properties are richly described in the schema, so the real gap is small. The description still contributes the critical constraint that images must be inline SVG or data: URLs — a restriction that matters for link-based delivery and is not stated at that level in 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?

States a specific verb and resource: 'Turn a recipe into a link that opens the icon in Liquid Composer.' An agent can tell this apart from liquid_validate and liquid_schema by the outcome (a link, not validation or a schema), though the siblings are never named.

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?

Usage is implied by the outcome ('opens the icon in Liquid Composer') but there is no explicit when-to-use/when-not guidance and no routing between this and liquid_validate or liquid_schema. The agent must infer that this is the final hand-off step.

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

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

The readOnlyHint=true and openWorldHint=false annotations already establish a safe, local, side-effect-free read. The description adds only the scope of content covered (recipes, layer patches, a guide) and says nothing about output shape, size, or how the schema and guide are combined in the response.

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 short sentence with no filler, so it is appropriately sized. However, the trailing 'and the guide' is a vague fragment that weakens an otherwise tight statement.

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 parameters and no output schema, the description carries the burden of explaining what comes back, and 'the guide' is never defined or its relationship to the schema clarified. It is minimally sufficient for a zero-arg schema fetch but leaves real ambiguity about the return payload.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; the empty schema is fully self-explanatory. Baseline 4 applies.

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 names the resource ('JSON Schema of recipes and layer patches') but never states the operation, and 'the guide' is left undefined. It is loosely distinguishable from liquid_open and liquid_validate, but only by inference, not by any explicit statement.

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?

There is no indication of when to call this versus liquid_open or liquid_validate, and no prerequisites or sequencing guidance. An agent must guess that this is the discovery step before validating or opening a recipe.

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

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

Annotations already cover the safety profile (readOnlyHint=true, openWorldHint=false), and the description adds genuine value by disclosing the return contract — "ok or the list of issues with their paths" — which is important since there is no output schema. It doesn't say how deep the validation goes (syntax vs schema conformance, which would relate to liquid_schema), leaving a behavioral gap.

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 compact sentence with the action front-loaded and the return behavior appended after the semicolon. No filler or restatement of the title.

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?

Return format and the read-only nature are covered, which is most of what a simple validator needs. However, with a completely untyped parameter and no output schema, the description should at minimum state what `recipe` accepts and what kinds of issues are reported; that gap leaves the tool under-specified.

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?

There is one required parameter with 0% schema coverage and an empty schema definition (`"recipe": {}`), so nothing tells the agent whether to pass a file path, an identifier, or the recipe body itself. The phrase "without opening it" hints it is not a handle, but the description never clarifies the expected shape or format of `recipe`.

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?

"Check a recipe" gives a specific verb and resource, and "without opening it" implicitly distinguishes it from the sibling liquid_open (which loads/opens). An agent can tell it apart from liquid_open, though liquid_schema is never addressed, so sibling differentiation is only partial.

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?

"Without opening it" implies the usage context: check validity cheaply before loading. But there is no explicit when-to-use/when-not statement, no mention of when to prefer liquid_open or liquid_schema, and no prerequisites or error conditions described.

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