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

No annotations provided, so description carries burden. Discloses cost ('near-zero-cost, reads a small JSON file'), return value ('null if no alert'), and workflow for clearing alerts with acknowledge=true. Could explicitly state read-only nature for default call.

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?

Very concise: three sentences, front-loaded purpose, no fluff, each sentence adds value.

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?

Complete for a simple tool with one parameter and output schema. Covers purpose, usage, parameter, return behavior, and 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?

Only one boolean parameter 'acknowledge' with clear meaning explained in description. Schema has 0% description coverage, so description adds full value.

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?

Clearly states verb 'Check' and resource 'Cacheout watchdog alerts'. Distinguishes from siblings by noting it's a near-zero-cost check, unlike other 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 when to use: 'at the start of tasks, before builds, or after errors', and what not to do: 'NOT on a polling loop'. Also provides post-alert workflow 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 indicate destructiveHint=true and idempotentHint=true. The description adds significant context: directories are preserved, only contents deleted, caches regenerate automatically, and dry_run behavior is detailed. No contradiction with 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?

The description is well-structured: a one-line summary, bulleted details, and a clear example of the return format. Every sentence adds value, and the most critical information (preview with scan_caches) is front-loaded.

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?

Given the tool's destructive nature (annotations), the description fully covers what happens, the recommended workflow, and the return value format via the output schema example. No gaps remain for an agent to misinterpret.

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 input schema properties (categories and dry_run) have detailed descriptions, so schema coverage is effectively 100% despite the 0% note. The description adds minimal extra meaning beyond those schema descriptions. 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 clearly states the action ('Clear specific cache categories to free disk space'), identifies the resource (cache categories), and distinguishes from siblings like cacheout_scan_caches by advising to use that tool first. The verb and outcome are specific and unambiguous.

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 provides explicit usage guidance: run cacheout_scan_caches first to see sizes, then pass slugs, and use dry_run=true to preview. It does not compare directly with smart_clean, but the workflow is clear and actionable.

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 description details the entire validate-then-write flow, including file writes, validation via socket or locally, atomic rename, SIGHUP, and polling. This goes well beyond the annotations which only hint at idempotency and non-destructiveness.

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?

The description is well-structured: purpose first, then numbered steps, then validation rules. It is slightly verbose but every part adds value.

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?

Given the tool's moderate complexity, the description covers the config structure, validation details, execution flow, and return format. No gaps remain.

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 schema description coverage at 0%, the description fully compensates by specifying validation rules for version, enabled, rules, webhook, and telegram, including exact required fields and value ranges.

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 clearly states 'Configure the autopilot policy for the headless daemon', which is a specific verb-resource combination. It distinguishes from siblings which deal with alerts, cache, health, etc.

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 provides no explicit guidance on when to use this tool versus alternatives. There are 11 sibling tools, but no mention of when to choose this one over them.

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 description goes well beyond annotations by detailing the dual-sample measurement (~1 second apart), thrashing detection criteria, trend behavior requiring multiple invocations, and mode differences (standalone vs app). This adds significant behavioral context that annotations alone do not cover.

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?

The description is front-loaded with the primary purpose and provides detailed, relevant information in a structured order. While thorough, some sentences could be merged to reduce length slightly without losing clarity.

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 adequately covers behavior, return envelope, and mode handling. It lacks error conditions or prerequisites, but for a health-read tool this is acceptable. Overall, it provides sufficient context 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?

The input schema has no meaningful parameters (only an empty params object), so the baseline is 4. The description does not need to elaborate on parameters and focuses on the tool's operation instead, which is appropriate given the schema's emptiness.

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 clearly states the tool retrieves 'macOS memory compressor health metrics' with specific outputs like ratio, rates, thrashing detection, pressure level, and trend. It differentiates well from sibling tools like cacheout_get_memory_stats and cacheout_system_health by focusing exclusively on compressor health.

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 explains how the tool works (dual-sampling, thrashing thresholds) but does not explicitly state when to use it over alternatives. No direct comparison with siblings or exclusion conditions are provided, leaving the agent to infer usage context.

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, destructiveHint=false, and idempotentHint=true. The description adds valuable details about the output format (total, free, used with human-readable sizes and percentages) and includes a concrete example, which goes beyond the 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?

The description is concise with three brief sentences plus a returns block. It front-loads the purpose, provides usage guidance, and gives output details without any redundant text.

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?

Given the tool's simplicity (zero parameters, safe read operation), the description fully covers what the agent needs: purpose, usage context, and detailed return format. The output schema is present, but the description's example enhances understanding.

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 input schema has 0% description coverage and contains a single empty params object. The description explicitly states 'No parameters required.', adding meaning that the schema lacks. This clarifies usage for the agent.

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 explicitly states the tool gets current disk space on the boot volume, with a clear verb 'Get' and a specific resource 'disk usage'. It distinguishes from sibling tools like cacheout_get_memory_stats (memory) and cacheout_check_alerts (alerts).

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 advises using this tool to check for disk pressure before deciding to clean, providing a clear use case. While it doesn't explicitly state when not to use it, the context is sufficient given the uniqueness of disk monitoring among siblings.

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 indicate readOnlyHint=true and idempotentHint=true. The description adds mode-dependent behavior (app mode vs standalone mode) and details about the memory_tier field. No contradictions with 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?

The description is well-structured, front-loading the purpose and listing all returned fields. The sample output is helpful but slightly lengthy. Every sentence adds value.

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?

Given the tool's complexity (many return fields, mode behavior), the description covers all aspects: what it returns, when to use, and mode details. Annotations and the implicit output schema are 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?

The tool has no actual parameters (the input schema's nested object has no properties). The description adds no parameter info because none is needed. Schema coverage is 0%, but that is irrelevant as there are no parameters to describe.

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 clearly states that the tool gets current system memory statistics on macOS, listing all returned fields and their purpose. It is distinct from sibling tools like cacheout_get_disk_usage and cacheout_get_compressor_health.

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 provides context for when to use the tool: 'check memory health before builds, heavy tasks, or when investigating performance issues.' It lacks explicit when-not-to-use or alternative tool references, but the usage context is clear.

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, destructiveHint, and idempotentHint. The description adds valuable context: explains the two modes (standalone RSS estimate vs app physical footprint), notes that sort_by_pageins is gated false, and describes the response envelope (mode, capabilities, data). No contradictions with 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?

The description is concise (5 sentences) and well-structured: first sentence describes purpose, then return format, mode details, sort key behavior, and finally parameters. No superfluous text.

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?

Given the tool's simplicity and annotations, the description covers all major aspects: purpose, mode dependency, sort key behavior, parameter defaults, and response structure. It adequately informs usage without missing critical details.

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 input schema already has detailed descriptions for both parameters (top_n and sort_by). The description adds context by linking sort_by to mode-dependency and mentioning the pageins gate. This goes beyond the schema, providing additional semantic value.

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 clearly states the action ('Get top processes by memory usage') and resource ('top processes on macOS'). It distinguishes itself from all sibling tools, which deal with caches, alerts, disk, etc. No ambiguity.

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 explains the tool retrieves top processes sorted by memory consumption, and clarifies mode-dependent behavior (standalone vs app). While it doesn't explicitly state when not to use it, the context is sufficient and no alternative tool exists among siblings.

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, destructiveHint, and idempotentHint. The description adds valuable behavioral context: mode-dependent result quality, the meaning of the partial flag, and the list of recommendation types. No contradictions with 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?

The description is well-structured: starts with overall purpose, then details mode behavior, partial flag, and includes an example output. Every sentence serves a purpose, no fluff. It is front-loaded and appropriately sized.

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?

Given the tool's complexity (multiple modes, partial flag, structured output), the description covers all essential aspects: mode-dependent behavior, partial flag semantics, and a full output schema example. It is complete enough for an agent to use correctly.

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 are no parameters, and schema description coverage is 100%. The description adds context about return format and mode-dependent behavior, which compensates for the lack of parameters. Baseline 4 for zero parameters 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?

The description clearly states the tool gets predictive memory recommendations from the Cacheout engine, listing specific recommendation types. This verb+resource combination distinguishes it from siblings like cacheout_get_memory_stats or cacheout_get_compressor_health.

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 explains mode-dependent behavior (socket, app, standalone) and when the partial flag is true, giving the agent context on when results are degraded. It does not explicitly compare to siblings or state when not to use, but the mode details provide sufficient guidance.

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 mark destructiveHint=true; description adds valuable context on dry-run vs execution, mode-dependent availability, and response capabilities map. Fully transparent about side effects and prerequisites.

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?

Well-structured: one-line summary, bold usage note, bullet list, mode details, return info. Front-loaded and concise given complexity; every sentence adds value.

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?

Covers core usage, interventions, modes, and response hints. Lacks error conditions or performance impact notes, but output schema handles return details. Adequately complete for a moderately complex 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?

Although schema description coverage is 0%, the description explains the intervention list, confirm flag purpose, and mode constraints. Target_pid is noted as reserved. Adds meaningful context 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?

Description clearly states 'Execute a memory reclamation intervention on macOS,' specifying the verb and resource. It distinguishes from sibling tools by focusing on memory purge/reclaim, unlike cache or disk utilities.

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?

Provides explicit two-step usage pattern (confirm=false then confirm=true) and lists available interventions with mode constraints. However, no direct comparison to sibling tools for when to use this vs alternatives.

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, destructiveHint=false, idempotentHint=true. The description adds that results are 'sorted by size (largest first)' and that it 'scans developer tool caches.' It does not disclose potential performance impacts, caching behavior, or authentication requirements. Given the strong annotation baseline, the additional context is modest but adequate.

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?

The description is extremely concise: three sentences plus a brief args/returns block. It front-loads the core purpose, then adds relevant detail (which caches, sorting), and ends with usage guidance. Every sentence is valuable. No repetition or 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?

Given the tool's moderate complexity (filter parameters, multiple cache categories) and the presence of an output schema (documented return format), the description covers the main intent and usage. It lacks nuance about the 'risk_level' and 'rebuild_note' fields in the return, but those are detailed in the schema. The description is complete enough for informed 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?

The tool description does not elaborate on the parameters. However, the input schema provides detailed descriptions for both 'categories' (list of slugs) and 'min_size_mb' (minimum size filter). Since schema_description_coverage is 0% (the description text covers none of the parameters), but the schema itself is comprehensive, the description adds no extra meaning. 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 clearly states the purpose: 'Scan macOS cache directories and report their sizes.' It specifies the resource (macOS caches) and verb (scan/report). It lists which developer caches are scanned, distinguishing it from sister tools like cacheout_clear_cache (cleans) or cacheout_system_health (health check). The tool is unambiguously a read-only analysis tool.

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 explicitly says 'Use this to understand what's consuming disk space before cleaning.' This provides clear context for when to invoke the tool (pre-cleaning) and implies it's not for cleaning itself. However, it does not explicitly mention when not to use it (e.g., not for checking alerts or general health). But the guidance is direct and sufficient for most agents.

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 mark destructiveHint=true. The description adds valuable context: the priority order of caches, that the server stops upon meeting the target, and the dry_run option. It does not contradict annotations and enhances understanding of side effects.

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?

The description is well-structured with a numbered priority list, example usage, and return format. It is front-loaded with the purpose. Minor redundancy could be trimmed, but overall efficient.

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 description explains the cleaning order, dry-run preview, and provides a sample return JSON. It covers most important aspects for an AI agent to use the tool effectively, though details about the 'cleaned' and 'skipped' fields are 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?

The description omits the 'free_memory' parameter, mentioning only target_gb, dry_run, and include_caution. The input schema has comprehensive descriptions for all four parameters, so the description adds little value and is misleading by omission.

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 clearly states the tool frees disk space by clearing caches in priority order, with a specific verb and resource. It explicitly positions itself as the primary tool for disk pressure management, distinguishing it from siblings like cacheout_clear_cache and cacheout_scan_caches.

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 explains when to use the tool (low disk space, need room for builds/swap) and provides a typical use case. It does not explicitly state when not to use it or compare with alternatives, but the context is clear enough for an AI agent to decide.

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, destructiveHint=false, idempotentHint=true. The description adds value by specifying the return value structure (mode, binary path, category list) and the use case for verification.

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?

The description is extremely concise with three short sentences covering purpose, return values, and usage. Every sentence provides necessary information without redundancy.

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 tool is simple with no parameters and an output schema. The description fully covers what the tool does, what it returns, and when to use it, making it complete for an agent.

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 input schema has 0% description coverage but only contains an empty object parameter. The description does not need to explain parameters as there are none of substance, and baseline for 0 parameters is 4.

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 clearly states the verb ('Get') and resource ('cacheout-mcp server status, mode, and available categories'), distinguishing it from sibling tools like cacheout_check_alerts and cacheout_clear_cache which have different purposes.

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 to verify the server is running and understand its capabilities', providing clear context. Does not explicitly exclude alternatives, but the purpose is specific enough that no exclusion is needed.

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 declare readOnlyHint and idempotentHint, and the description adds valuable behavioral details: health score formula, penalties, and mode-dependent behavior (socket vs standalone). No contradictions with 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?

The description is well-structured: purpose first, then return details, mode explanation, and formula. Every sentence is informative, and the code-like formula is concise.

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?

Given no required parameters and the presence of an output schema (indicated), the description adequately covers the tool's behavior, mode, formula, and return format. No gaps identified.

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 are no parameters to document (schema has no properties), and the description correctly notes 'No parameters required.' With 0 parameters, baseline is 4, and no additional semantics are needed.

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 clearly states 'Get overall system health score with alerts', specifying the resource and action. It does not explicitly differentiate from siblings like cacheout_check_alerts or cacheout_get_compressor_health, but the purpose is distinct enough.

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 explains two modes (socket vs CLI/standalone) with latency implications, providing some context on when to use. However, it lacks explicit guidance on when not to use this tool or alternatives among siblings.

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