Front-End Checklist

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

Annotations already declare readOnly, idempotent, openWorld, non-destructive, so safety is covered. The description adds real behavioral context: it automatically fetches page source over the network and returns a prioritized issue list, and the workflow tells the agent what the next step is. It does not mention fetch failures/timeouts or rate limits, keeping it short of a 5.

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 core action, then scoping, then a compact workflow arrow-chain. Every sentence carries information, though the bolded '**Use this tool**' and '**Workflow:**' emphasis is slightly marketing-flavored for a tool definition.

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 3-parameter read tool with an output schema, the description covers purpose, network-fetch behavior, sibling differentiation and the follow-up tool. It leaves out failure modes (unreachable/blocked URLs, redirects) and whether results are cached, but nothing essential for correct invocation 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 url, focus and minPriority are all documented in the schema itself. The description adds no syntax or format detail beyond the schema (the https/private-IP restriction it mentions is already in the url parameter description). 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+resource ('Fetches a public URL and audits its HTML against frontend best practice rules') and immediately distinguishes itself from the sibling review_code by noting it works on a live site 'without manually pasting HTML'. An agent can route between audit_url and review_code from the description alone.

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?

Explicitly says when to use it (checking a live website) and names the alternative behavior it substitutes for (review_code's manual HTML path). The workflow line chains it to fix_rule for remediation. No explicit when-not condition (e.g. non-public or non-https URLs), which is the only gap.

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, idempotentHint, and non-destructive, so safety is covered. The description earns credit for disclosing mode-dependent behavior (no code → verification guidance; code → heuristic analysis with compliance status), the heuristic caveat, and that issues include a fix prompt. It stops short of detailing scoring thresholds or result structure, but the output schema covers returns.

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 core action and the PROACTIVE cue, then structured with a bolded Workflow block. It is slightly longer than needed (the mode description and workflow overlap), but every section carries actionable 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?

A read-only, idempotent analysis tool with an output schema: the description covers both invocation modes, the workflow position among siblings, and remediation hand-off. Nothing an agent needs to select or call it correctly 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 both parameters are documented, so the baseline is 3. The description adds only marginal meaning, clarifying that 'code' is optional and changes the tool's behavior between guidance and analysis modes.

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 ('Checks code against a specific frontend rule') and scopes it to HTML/CSS/JS review, which no sibling does — the others fetch, explain, fix, or review broadly. An agent can distinguish it from get_rule and review_code without opening the 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?

Explicit when-to-use ('Use PROACTIVELY when reviewing HTML/CSS/JS code'), explicit triggers ('after search_rules finds relevant rules, or when review_code flags a specific issue'), and explicit follow-ups (fix_rule for remediation, explain_rule for rationale). Alternatives and sequencing are fully covered.

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, idempotentHint, and non-destructive behavior, and an output schema exists, so the safety and return profile is covered elsewhere. The description only adds that explanations include background/impact and that categories connect related concepts — useful but modest added context.

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 core purpose in the first sentence, then structured under a bolded Workflow. Slightly dense with bolded emphasis and multiple sibling references, but every clause carries routing or scope 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 a rich annotation set, a fully documented single parameter, and an output schema, the description need not explain returns. It supplies the missing piece — when to invoke it and which siblings to pair it with — though it could clarify how it differs from get_rule.

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?

One required parameter (slug) with 100% schema description coverage, so the schema does the work. The description adds no format or sourcing detail for the slug beyond what the schema states; 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: retrieves the educational explanation for a frontend rule, and adds scope (why the rule matters, background, impact). It does not explicitly contrast itself with the close sibling get_rule, so an agent must infer the difference between the 'rule' and its 'explanation'.

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?

Explicit triggers ('when the user asks "why"', 'when explaining code review feedback') and a named workflow: use after fix_rule for educational context, pair with check_rule to validate understanding, search_rules to find related practices. The when-to-use and alternatives are both 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?

Annotations already declare readOnlyHint/idempotentHint/non-destructive, so the safety profile is covered. The description adds genuine context beyond that: the output is step-by-step remediation guidance with a priority level for triage, and codeSnippet enables context-aware fixes. No auth or rate-limit details, but none are critical for a read-only prompt fetch.

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-loads what is retrieved, then usage and workflow in clearly delimited sections. Slightly verbose with bolded emphasis, but every sentence carries actionable routing or behavioral 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?

Output schema exists so return values need no explanation, annotations cover safety, and usage is fully specified. Only marginal gaps (e.g., what kind of rule slugs are valid) remain, which the sibling get_rule/search_rules context covers.

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 description does not restate slug or codeSnippet semantics beyond what the schema documents. The mention of 'priority level' concerns the response, not an input, so the baseline 3 is appropriate.

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 ('Retrieves the fix/implementation prompt for a specific rule'), and the workflow sentence distinguishes it from get_rule (context) and explain_rule (understanding). An agent can tell what it returns without opening the 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?

Explicit triggering conditions ('Use PROACTIVELY after identifying issues in frontend code') plus a named workflow: call after review_code or check_rule. Alternatives are named with their distinct roles, leaving little to inference.

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, idempotentHint and non-destructive, so the safety profile is covered. The description adds the bulk-fetch/efficiency trait, but 'full rule details for every rule' subtly conflicts with the schema's includeContent default of false (title, description, prompts, metadata only) – an agent could wrongly assume the full MDX body always comes back.

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 value proposition and the efficiency contrast in the first two sentences, which is well structured. However, the trailing enumeration of all twelve checklist slugs duplicates the schema enum verbatim and consumes tokens without adding 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?

Output schema exists, so return shape needn't be explained, and usage/alternatives are covered. The only real gap is the ambiguity between 'full rule details' and the default includeContent=false behavior, which could mislead about payload size and content.

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 both parameters are documented there, so baseline 3 applies. The description only re-lists the checklist enum values, adding no semantics beyond the schema, and says nothing about includeContent.

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 ('returns full rule details for every rule in a curated checklist') and explicitly positions itself against siblings by calling out get_rule and get_workflow. An agent can distinguish it from single-rule tools 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?

Gives clear context ('when you need the complete rule content for an entire checklist to perform a comprehensive audit or code review') and names get_rule as the less efficient alternative. It lacks an explicit 'use get_rule instead when you only need one rule' exclusion, but the bulk-vs-single tradeoff is easy to infer.

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, idempotentHint, non-destructive and closed-world, so the safety profile is fully covered by structured data. The description adds the compact/checklist nature of the output but nothing about size limits, rate limits, or whether categories are fixed. Adequate but not rich on top of annotations.

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 core purpose and tightly organized into a purpose sentence and a workflow line. The bold '**Use PROACTIVELY**' and workflow pairing are useful, not padding, though the second paragraph slightly restates the first.

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 no explanation, and annotations cover the safety profile. The description supplies the usage context and sibling routing an agent needs; only minor behavioral details (e.g., category source, typical list size) are absent.

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% with enum values documented for both format and priorityFilter, so the schema carries the parameter semantics. The description only echoes 'filtering by priority and multiple output formats' without adding syntax or defaults beyond 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?

The description states a specific verb and resource ('Returns a compact, actionable checklist of rules for a category') and explicitly contrasts itself with siblings by naming check_rule for validation and get_rule for detailed guidance. An agent can tell it apart from get_rule and get_checklist_rules without opening schemas.

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 well specified: '**Use PROACTIVELY** for CI/CD integration, quick audits, or generating checklists' plus the workflow note about pre-deployment and team handoffs. Alternatives are named (check_rule, get_rule), though no explicit 'when-not-to-use' condition is given.

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/closed-world, so safety is covered. The description adds genuine behavior beyond that: the return format (Markdown with code examples), included prompts and metadata, related-rules enrichment, and the failure fallback ('returns suggestions for similar rules'). It stops short of describing the error surface in more detail, but the added context is substantive.

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 core action, then bolded workflow and related-rules sections that are scannable. It is somewhat long for a simple getter, but each block (usage, workflow, related) carries recoverable information rather than 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?

Output schema exists, so return-value details are a bonus rather than a requirement, yet the description still summarizes content and prompts. Combined with the workflow guidance and fallback behavior, an agent has everything needed to call this tool correctly in context.

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 both parameters (slug, includeUrl) are documented in the schema itself, so baseline is 3. The description adds a small amount via the missing-slug behavior but doesn't clarify slug format or the effect of includeUrl beyond what the schema already says.

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?

Specific verb and resource ('Retrieves a single frontend development rule by its unique slug') with clear scope. It also names its siblings (search_rules, check_rule, fix_rule, explain_rule) so an agent can distinguish this lookup tool from validator/fixer tools without opening their schemas.

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?

Explicitly states when to use it ('Use PROACTIVELY when reviewing or debugging frontend code') and where it fits in the workflow (after review_code or search_rules). It also points to the natural follow-up tools and their conditions, leaving little to inference.

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, idempotentHint, non-destructive and closed-world, so safety is covered. The description adds genuine behavioral context beyond that: the result is ordered and curated, and it is meant to be consumed before per-rule calls. It does not describe size/pagination of the returned sequence, but with an output schema present that burden is light.

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 purpose and the proactive-usage cue, and the ordering guidance is compact. However, the twelve-item workflow list is duplicated from the enum, which is wasted space an agent can already read 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?

For a single-enum, read-only retrieval tool with an output schema, the description supplies everything needed: what it returns, when to call it, and how it fits into the get_rule/check_rule pipeline. Return-value details are correctly left to the output schema.

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 enum already enumerates all twelve slugs. The description merely repeats the same list verbatim, adding no extra meaning about constraints or how to choose a workflow slug — the baseline of 3 applies when the schema does the work.

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 ('Returns a curated, ordered sequence of rules for a specific checklist workflow') and clarifies the unit of work (a named workflow, not an individual rule). It also distinguishes itself from siblings by positioning itself as the entry point before get_rule and check_rule.

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?

Explicitly says 'Use PROACTIVELY when performing comprehensive audits or setting up new projects' and gives a concrete ordering: this tool FIRST, then get_rule per step, then check_rule to validate. The condition and the alternatives are both 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?

Annotations already declare readOnlyHint, idempotentHint, openWorldHint=false and destructiveHint=false, so the safety profile is fully covered. The description adds the useful detail that each category comes with rule counts and names sample areas, but says nothing about ordering, storage, or refresh behavior. Adequate, 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?

Front-loads the core behavior, then gives workflow guidance in a compact labeled block. The bolded 'PROACTIVELY' and workflow header add mild visual noise but the content is dense and earns its space.

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-value documentation is unnecessary, and the description covers purpose, timing, and downstream chaining. Nothing an agent needs to call this zero-arg list tool correctly 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?

The tool takes zero parameters, so there is nothing for the description to disambiguate and the baseline applies. Nothing in the description misleads about inputs.

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 ('Lists all available rule categories') plus the payload detail (rule counts), which is exactly what an agent needs to know before calling. It is clearly distinguishable from siblings like search_rules and review_code, which are named as follow-ups.

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?

Explicitly prescribes the when ('Use PROACTIVELY at the start of a frontend project review') and the sequencing ('Use FIRST when starting a comprehensive audit'), then names the alternatives to chain into (search_rules, review_code). No inference required.

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 establish readOnly/idempotent/non-destructive, and the description adds substantive behavior beyond them: the review is heuristic and non-exhaustive, issues are only reported when 'provable from the snippet,' and a clean result means 'no provable static issue found' rather than clean code. This calibrates the agent's trust in the output, which is exactly the kind of context annotations 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?

Purpose and the 'use FIRST' directive are front-loaded, and the bolded headers make scanning easy. The workflow block is somewhat repetitive with the opening paragraph's guidance, but every sentence is on-topic 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 an output schema present, the description needn't explain return values, and it correctly focuses on when to call, what the tool can and cannot prove, and how to chain into sibling tools. Complete enough for correct invocation; the only minor gap is that it never mentions the focus/minPriority defaults explicitly in prose.

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 code, focus, and minPriority. The description only implicitly reinforces defaults ('detects the code type', auto-detect) without adding syntax or format detail. Baseline 3 applies when the schema carries the parameter burden.

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 (review) and resource (HTML/CSS/JS frontend code) and immediately characterizes the method: 'conservative, non-exhaustive static heuristic review ... against multiple frontend best practice rules simultaneously.' This clearly separates it from siblings like fix_rule, get_rule, and search_rules, which are retrieval rather than analysis 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?

Explicitly says 'Use this tool FIRST' for any frontend code review and lays out a workflow: follow up each issue with fix_rule or get_rule, and if nothing is returned treat that as inconclusive and continue with search_rules/get_rule. When-to-use and what-to-do-next are both 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 establish readOnly, idempotent and non-destructive, so safety is covered. The description adds useful context beyond them: matches return summary information only, and get_rule is required for full details and code examples. It stops short of describing pagination/cursor behavior, which is left to the 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?

Front-loaded with the core action and an emphasized proactive-use cue, followed by a compact workflow. Every sentence earns its place, though the bolded PROACTIVELY and workflow block make it slightly longer than strictly necessary.

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-value detail is unnecessary, and annotations plus the schema cover safety and parameters. The description completes the picture by placing the tool in a discovery workflow. Only pagination nuances are unaddressed, which the schema handles.

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 query, categories, priorities, limit and cursor are already documented in the schema. The description's mention of searching by technology/concern/pattern maps loosely onto query and categories but adds no syntax or format detail beyond the schema. Baseline 3 is appropriate.

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 ('searches and filters frontend development rules') and enumerates the filter axes (technology, concern, patterns). It clearly distinguishes itself from siblings like get_rule ('full details') and list_categories ('see available areas').

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?

Explicitly says to use it PROACTIVELY when working on frontend code, and gives a concrete three-step workflow naming list_categories as the entry point and get_rule as the follow-up. When-to-use and alternatives are both spelled out.

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