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

With no annotations, the description carries the burden and does so well: it discloses CI/PostToolUse parity, the exact rule categories run, the html-vs-jsx behavioral split, and that coverage info is always returned. It omits failure modes or output detail beyond coverage, but for a pure lint operation the disclosed context is substantial.

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 sentences, all load-bearing: scope, when-to-use, and return-value caveat. The self-verification instruction is front-loaded and 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?

No output schema exists, but the description compensates by stating the response always includes coverage info and that manual rules cannot be auto-checked. Timing, scope, and return expectations are all present; only deeper output structure is left 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% and the sourceType enum is already described in the schema. The description's mention of composition rules for HTML corroborates but does not extend the sourceType semantics, 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 (lint), resource (full HTML/JSX source), and the rule system it validates against (melta-ui rules). It further scopes what is checked (class rules, html-attr rules, composition), which separates it from siblings like check_rule and get_rules.

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?

"Use this AFTER generating UI code to self-verify before presenting it" gives explicit timing and intent, which is real guidance. It does not name an alternative tool or state when not to use it (e.g., single-rule checks via check_rule), so it falls short of a 5.

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?

With no annotations, the description carries the full burden. It does disclose the return payload ('violations with reasons and alternatives'), which is the most useful behavioral fact, but it never states that the call is non-mutating, requires no auth, or what an empty result looks like. 'Check' implies a read, but that is inference rather than disclosure.

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 filler, and the action is front-loaded ahead of the return-value note. Every clause 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, read-only checker with no output schema, the description is nearly complete: it covers what is checked and what comes back. It could be fuller by noting the clean-result case or its relationship to check_html, but nothing critical 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% and the single parameter is fully documented in the schema with a concrete example. The description adds no extra meaning about the classes string (e.g. format constraints or whether multiple strings are accepted), so the baseline of 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?

The description gives a specific verb (check) and resource (class strings against this design system's prohibition rules), which is enough to separate it from get_rules or get_token. It does not explicitly differentiate itself from the sibling check_html, so an agent must infer that one takes class strings and the other markup.

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 statement of when to use this versus check_html, get_rules, or get_token, and no prerequisites such as running it before shipping markup. Usage is only implied by the phrase 'this design system's prohibition rules'.

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?

With no annotations, the description carries the full burden and does meaningfully disclose the return shape: per-state specs (disabled/loading/open/empty with delta class strings and aria changes) and anatomy parts with element/roles/class. This is real behavioral context beyond a bare "get," though it omits any statement of read-only safety, permissions, or error behavior.

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 tool's purpose and contents, with no filler. The first sentence is dense with comma-separated field lists, but each clause maps to actual returned data and 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?

With no output schema and no annotations, the description must describe return values, and it does so thoroughly across variants, sizes, accessibility, HTML sample, stateSpecs, and anatomy. What remains missing is operational context (read-only nature, error cases on an unknown id), which is minor for a lookup tool.

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% for the single id parameter, including example values, so the schema already does the work. The description adds no syntax, format, or lookup semantics for id beyond what is structured. 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?

"Get component metadata" states a specific verb and resource, and the description then enumerates exactly what that metadata includes (variants, sizes, accessibility requirements, HTML sample, stateSpecs, anatomy parts). The resource is unambiguous against siblings like get_token, get_rules, and check_html.

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 resource: given a component id, fetch its metadata. The only explicit guidance — "Prefer these structured fields over inferring states from the HTML sample" — concerns how to interpret the output, not when to choose this tool over siblings such as check_html or get_token. No alternatives or exclusions are named.

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?

No annotations are provided, so the description carries the full behavioral burden. It discloses the data source (rules.json) and corpus size (107), which is useful, but says nothing about whether all rules are returned by default, pagination/limits on a 107-item result, or permissions. Adequate but incomplete for a tool with zero annotation coverage.

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 what the tool returns and immediately followed by the routing condition. No sentence is redundant and nothing is buried.

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 and no annotations, so the description should ideally describe the returned rule shape or the unfiltered default behavior. It covers the lookup purpose and filters adequately, but an agent still cannot predict what a call with no arguments yields.

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% with two enum-constrained params and descriptive text for all three filters. The description merely restates that category/severity/detector filtering exists, adding no syntax, default, or combination semantics 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?

The description names a specific verb (Get) and resource (melta-ui prohibition rules from rules.json), gives the corpus size (107 total), and explicitly distinguishes the tool from its closest sibling check_rule. An agent can tell it apart from check_rule, search, and get_token without opening any schema.

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?

"Use this to retrieve manual/contextual rules that check_rule cannot auto-detect" gives a clear selection condition and names the alternative tool. It stops short of stating when not to use it (e.g. when searching for arbitrary content, where `search` applies), so it is clear context without explicit exclusions.

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?

With no annotations, the description carries the full burden, and it does disclose the return shape ('token object with its value and class mapping'), which is genuine context. However, it says nothing about what happens on an invalid path, whether the lookup is exact-match or prefix-tolerant, or any read-only guarantee beyond the implicit verb.

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 short sentences, front-loaded with the action and the key, followed by the return value. No filler or redundant restatement of the name.

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 single-parameter read tool with full schema coverage, the description supplies both the lookup semantics and a summary of the returned object, which is what an agent needs to invoke it. Only error/miss behavior is left unaddressed, which is a minor gap.

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 schema already documents 'path' with illustrative dot-path examples. The description's mention of dot-path adds no syntax or format detail beyond that, 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 and resource ('get a design token') plus the lookup mechanism ('by dot-path'), which is enough to distinguish it from siblings like get_component or check_rule. It stops short of explicitly contrasting itself with any named sibling, so it lands at clear-but-undifferentiated.

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 implies the use case (resolving a single token by path) but never states when to reach for this tool over search or get_rules. Usage is inferable from the resource name rather than 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?

With no annotations, the description carries the behavioral burden and does disclose two substantive traits: a hard cap of 20 results and a truncation flag when more matched. It stops short of explaining result ordering/relevance or that there is no pagination parameter to retrieve results beyond the cap.

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 compact sentences, front-loaded with the action, then matching scope, then result behavior. Every sentence adds information and nothing is repeated from the schema.

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?

No output schema and no annotations, so the description must cover behavior itself; it does so for result count and truncation. Gaps remain around relevance ordering and whether results are typed/labeled, and there is no hint of how to get past the 20-result cap.

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 there is only one parameter, so the schema already documents 'query' fully. The description adds what the keyword is matched against, which helps query construction, but no syntax, operators, or format rules beyond the schema's examples.

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 ('Search across tokens and components by keyword') and enumerates the fields matched against (names, values, class strings, descriptions). This implicitly separates it from the get_* siblings, which fetch by identity, though no sibling is named 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: keyword search is what you reach for when you don't have an exact token/component name. The description never states when to prefer it over get_token or get_component, nor any exclusions, so the agent must infer the routing itself.

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