Facade UI

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

Annotations already declare readOnly, idempotent, non-destructive, so the safety profile is covered. The description adds genuinely new behavioral context: Pro sources require a license key in the Authorization header, which an agent cannot learn from the annotations or schema. It stops short of describing failure behavior when the key is missing.

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?

Two sentences, zero waste, with the payload contents front-loaded and the auth caveat second. Every clause carries information.

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 enumerates what is returned (docs, install command, usage example, full source) and flags the license requirement. Only the error/unauthorized path is left unstated, a minor gap for a read-only single-item fetch.

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 single 'name' parameter is documented with a concrete example slug and a pointer to list_components. The description adds nothing beyond the schema, so the baseline 3 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?

States a specific verb ('Get') and resource ('one Facade item') and enumerates the payload: docs, install command, usage example, full source. This clearly distinguishes it from list_components (which enumerates items) and get_install_command (which returns only the command), though the overlap with the latter is not explicitly addressed.

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 phrase 'for one Facade item' implies this is the per-item fetch versus the list, but there is no explicit when-to-use/when-not guidance and no mention of when to prefer get_install_command over this bundled call. Usage is inferable but not stated.

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 declare readOnly, idempotent, non-destructive and closed-world, so the bar is lower; the description still adds real value by making clear it only returns a command string rather than performing an installation, and that the command targets the current project. It does not state the return shape (bare string vs object), which is the remaining 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?

One sentence, front-loaded with the verb and the artifact returned, with zero redundant clauses. Every element 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?

For a one-parameter, fully annotated, read-only helper this is essentially complete: what it returns, for which items, and where the command applies are all covered. The only omission is what the returned value looks like, and there is no output schema to fall back on.

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 a single parameter at 100% schema description coverage, the schema already documents the slug array, its item format and minItems. The description's 'one or more Facade items' reinforces plurality but adds no new syntax or constraint detail, so baseline 3 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?

States a specific verb ('Return') and a precise resource ('the shadcn CLI command that installs ... Facade items'), plus the scope ('into the current project'). It is clearly distinct from list_components, get_component and suggest_page, though it never names them to reinforce the contrast.

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 only implied: an agent can infer you call this after choosing item slugs, but there is no explicit when-to-use, when-not-to-use, or pointer to the sibling that resolves a slug (get_component / list_components). Nothing misleading, but nothing guiding either.

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 declare readOnly, idempotent, non-destructive, and closed-world behavior. The description adds one useful operational fact: an unfiltered call returns the complete catalog. It says nothing about pagination, ordering, or result size limits, which matters for a catalog listing.

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 with the domain context front-loaded, followed by filter capabilities and the no-filter behavior. Nothing is repeated or padded.

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 should sketch what a returned item looks like (identifier, name, tier, category) so an agent can chain into get_component or get_install_command. It mentions only 'every item is returned', leaving the result shape and ordering unspecified.

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%, including enum descriptions for kind and tier, so the schema already explains every parameter. The description only restates the filter names and their optionality, adding no new semantics such as combining filters or match behavior.

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 states a specific verb and resource ('List Facade components and blocks') and immediately clarifies what those things are ('animated React + Tailwind sections for local business, real estate and agency sites'). This distinguishes it from the sibling get_component, which retrieves a single item by name.

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 states that all filters are optional and that no filter returns every item, which is useful context. However, it never names an alternative (e.g., get_component for a single item, suggest_page for recommendations) or states when filtering is preferred over listing everything.

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 declare readOnly, idempotent, non-destructive, and closed-world behavior, so the safety profile is covered. The description adds only the shape of the result ('ordered list of Facade blocks'), with no note on determinism, coverage limits, or what happens for unrecognized business types.

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?

One front-loaded sentence with no filler and the key scope in the first clause. The parenthetical examples are slightly redundant with the schema but not wasteful.

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?

For a simple one-parameter, read-only tool this is close to adequate, but with no output schema the description should say more about what a returned 'Facade block' entry looks like (names, identifiers, ordering semantics).

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 'business' with the same examples. The description's examples largely duplicate the schema, so no meaningful extra parameter guidance is provided beyond baseline.

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 (suggest) and resource (an ordered list of Facade blocks for a complete page), plus concrete business-type examples that make the intent unambiguous. It does not explicitly contrast with siblings like list_components, but the verb 'suggest ... ordered list ... to build a complete page' is distinguishable from plain listing.

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: call this when you need a page plan for a given business type. There is no explicit statement of when to prefer it over list_components/get_component, nor any prerequisites or exclusions.

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