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

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety profile is covered and the description does not contradict them. It adds genuine behavioral value by disclosing that output is a plan (ordered blocks, install commands, page.tsx scaffold, complete templates) rather than a mutation, though this overlaps the output 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?

Two sentences, front-loaded with the verb and resource before the return description. Every clause carries weight and there is no filler, though the return summary is only moderately compact.

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?

An output schema exists, so return values needn't be spelled out, and the purpose is well covered. However, with 0% schema description coverage, the two non-required parameters (includePro, packageManager) are left fully undocumented in both schema and description, leaving the definition incomplete for correct invocation.

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 0%, so the description must carry the burden of explaining the three parameters. It illustrates what 'intent' looks like via examples, but includePro and packageManager are never mentioned, leaving two parameters entirely undefined.

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+resource ('Plan a page from Ballmac UI blocks') and illustrates with two concrete intent examples, making the tool's function unmistakable. It does not explicitly name or contrast with siblings like search_items or get_setup, so differentiation is implied rather than stated.

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 examples ('SaaS landing page with pricing and FAQ', 'login screen') imply when to reach for this tool, i.e., when the user describes a whole page rather than a single component. There is no explicit when-not guidance or named alternative for narrower lookups handled by sibling tools.

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 and openWorldHint annotations already establish that this is a safe, non-mutating, externally-sourced read. The description adds the provenance detail that these are the same examples shown on the item's page, but says nothing about format, language, size, or behavior when an item has no examples.

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, and the resource is front-loaded. The parenthetical adds a bit of value rather than padding.

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 read tool with no output schema, the description should at least identify the key's format and whether the result is a code block or a list. What exists is minimal but not misleading.

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 0% and the single 'name' parameter is completely undocumented in the schema. The phrase 'for an item' weakly implies that 'name' identifies the item, but the description never states whether it expects a slug, ID, or display name, so the gap is only partially closed.

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 resource (working example code) and scope (for an item), which separates it cleanly from get_item, get_install_command, and get_setup in the sibling list. It is clear what the tool returns, though the description never names the 'name' argument it operates on.

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 when-to-use or when-not-to-use guidance. The only routing hint is the implicit contrast with get_item, and nothing tells the agent why it would choose examples over install commands or setup instructions.

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 readOnlyHint=true and openWorldHint=true, so safety is covered; the description adds genuine extra context beyond that—prerequisite registry setup, the free-vs-Pro distinction, and the @ballmac-pro/<name> naming convention. It doesn't state rate limits or pagination, but for a command-generator that's minor.

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 dense, front-loaded sentences that lead with the purpose and then layer the setup prerequisites. Every sentence carries workflow information with no filler, though the back half packs multiple conditional rules that could be slightly clearer.

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?

An output schema exists, so return values need not be explained, and the description covers the registry/setup workflow and Pro handling well. The main gap is the undocumented `packageManager` parameter, which leaves the definition slightly incomplete for a tool whose output varies by package manager.

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 0% and neither parameter is documented in the schema. The phrase 'one or more items' loosely implies the `names` array, but `packageManager` (an enum of pnpm/npm/yarn/bun) is never mentioned in the description, so the agent gets no guidance on a parameter that materially changes the output.

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 resource ('the shadcn CLI commands to add one or more items to the user's project'), so an agent knows it returns install commands rather than items or examples. It implicitly separates itself from the setup steps it names, but does not explicitly reference sibling tools like get_setup or get_item, so it stops short of full sibling differentiation.

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?

Gives concrete workflow conditions: run `setup` once if components.json lacks the @ballmac registry, then `add`; `byUrl` works without setup for free items; Pro items need `proSetup`. This is clear when-to-use guidance, though it doesn't name the alternative sibling tools or state exclusions explicitly.

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=true). The description adds genuinely useful non-annotation context: source is only returned for Pro items when the server holds BALLMAC_LICENSE_KEY, the `licence` field signals this, and includeSource=false yields a shorter answer. It stops short of describing failure behavior for unknown names or response size.

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?

Front-loaded with the scope statement, then the return inventory, then the licence caveat, then the includeSource tip. Dense but every clause carries information; only the field enumeration runs slightly long.

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 must describe returns and it does so thoroughly, plus it flags the licence-gated source. Remaining gaps are error behavior for an invalid name and any indication of response size for large items.

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 0% for both parameters, so the description carries the burden. It explains includeSource well (false = shorter answer), but `name` is never characterized — no format, ID vs slug, or lookup semantics — leaving the required parameter undocumented in both schema and prose.

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?

Names a specific verb+resource ('Everything about one item') and enumerates the exact payload the agent receives: description, import line, props, keyboard behaviour, dependencies, composition hints, template pages, source. That clearly separates it from list_items/search_items, though it never names a sibling explicitly.

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 rather than stated: 'Everything about one item' signals the deep-fetch tool versus the list/search siblings, but there is no explicit when-to-use vs get_examples, search_items or get_install_command. The only concrete guidance is the includeSource tradeoff, which is parameter-level, not tool-level.

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 readOnlyHint=true and openWorldHint=true, so the safety profile is covered and the bar is lower. The description adds topic scope (init, registry, theme, requirements) but discloses nothing about freshness, source, or whether output is static docs. Adequate but not rich.

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 topic, with no filler. The parenthetical list is slightly compressed but every element earns its place by describing scope.

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?

An output schema exists, so return values need not be explained. However, for a setup-guidance tool with an undocumented parameter and no usage routing, the description leaves the agent guessing about when this belongs in the workflow.

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 0% for the single packageManager parameter, and the description never mentions it. The parenthetical content list does not hint that setup instructions vary by package manager, so the meaning of this enum parameter is left entirely to the raw enum values.

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 (project setup for Ballmac UI) and enumerates the content it covers (shadcn init, registry entry, optional theme, requirements), so an agent can tell it apart from get_install_command or get_examples. It is clear but does not explicitly say it returns setup/preparation instructions, leaning on the name and title.

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?

No when-to-use or when-not-to-use guidance is given, and no alternative is named. An agent cannot tell from the description whether to call this before get_install_command or instead of it, even though those siblings clearly overlap in the setup workflow.

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 readOnlyHint=true and openWorldHint=true, so the safe-read profile is covered. The description adds that counts and category groupings are returned, but this largely overlaps the output schema, and it discloses nothing about cost, caching, or ordering.

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 compact sentences with no filler, and the key value (the returned counts) plus the chaining instruction are front-loaded. The opening is slightly awkward but nothing is wasted.

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 an output schema, no parameters, and safety annotations present, the description only needs to say what the tool enumerates and how to use it, which it does. An agent has enough to call it correctly and route the output to list_items.

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 no argument semantics to explain and the baseline is 4. The description correctly implies a no-argument enumeration.

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 the resource (components, blocks, templates and their grouping categories) and that it returns counts, which is a concrete purpose beyond the bare name. It is clear what the tool reveals, though the 'How many…' phrasing is slightly indirect rather than a crisp verb+resource 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?

It explicitly tells the agent how to consume the result: 'Use the names as the category filter of list_items,' which links this enumeration tool to a concrete follow-up sibling. It stops short of explicit when-not-to-use guidance or naming alternatives like search_items.

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 readOnlyHint=true and openWorldHint=true, so the safety profile is covered structurally. The description adds useful domain context (what a component/block/template is and that categories span primitives, motion, hero, pricing, marketing) but says nothing about result size, ordering, or pagination.

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 carries the purpose and filters, followed by a short pointer to list_categories. The parenthetical for category is dense but earns its space; nothing is redundant.

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 an output schema present, return values need no explanation, and the description covers the zero-required-parameter filtering surface plus the valid-name lookup path. Only ordering/pagination behavior is left unaddressed.

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 0%, so the description carries the load, and it does: it explains what each kind value means and spells out the three flavors of the free-form 'category' string, which the schema leaves entirely undescribed. The tier enum values are not explained, but free/pro is self-evident.

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 concrete verb and resource ('List components, blocks or templates') and immediately scopes the optional filters. It does not name a sibling alternative (e.g., search_items), so it is clear but not differentiated from related listing tools.

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 clear usage context: filtering is optional and can be driven by kind, category, or tier, and it directs the agent to list_categories for valid names, establishing a dependency ordering. It stops short of stating when to prefer this over search_items or get_item.

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 readOnlyHint=true and openWorldHint=true, so the safety and open-world profile is covered. The description adds useful traits beyond that: synonym handling and that results include when-to-use guidance. It still says nothing about ranking behavior, result volume, or how 'best matches' are determined.

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 tight paragraph, front-loaded with the core 'search by need' idea followed by examples and synonym hints. Nothing is padded, though the synonym list is somewhat incidental detail rather than essential routing 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?

An output schema exists, so the description need not explain return values, and the 'when-to-use guidance' note confirms results are self-describing. What's missing is any handling of the filtering parameters and any contrast with the list/get siblings, but for a straightforward search entry point this is close to sufficient.

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 0%, so the description carries the burden, and it does explain the query parameter's natural-language and synonym semantics with examples. It is silent on the kind enum (component/block/template) and the limit bound (1-30), so two of three parameters get no semantic help.

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 gives a specific verb+resource (search items by natural-language need) and supports it with concrete query examples ('chat input with attachments', 'pricing section'), so an agent knows exactly what gets indexed. It does not, however, distinguish itself from siblings like list_items or get_item, leaving the boundary 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?

Usage is implied by 'search by what the user needs' and the example queries, which is enough to know it is a natural-language lookup tool. There is no explicit when-to-use versus when-not, and no mention of the obvious alternative list_items for browsing or get_item for retrieval by id.

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