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

With no annotations, the description carries the full burden. It says extraction goes to a temp directory and that a summary of errors/warnings/notices is provided, but it does not disclose whether the temp directory is cleaned up, what happens if the directory already exists, or what the summary structure looks like. This is partial transparency.

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 only two sentences, front-loaded with the core action, and every word serves a purpose. No redundancy or fluff.

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 has 2 simple parameters and no output schema, so the description needs to explain return behavior. It mentions 'summary of issues found' but not the exact format or whether extracted files persist after execution. Adequate but with gaps in post-extraction behavior and return structure.

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 both parameters described in the schema (zip_path and output_dir, including default). The description doesn't add significant extra meaning beyond echoing the temp directory default; 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 clearly states the tool's function: 'Extract and summarize an Ahrefs site audit ZIP file.' It specifies the resource (Ahrefs site audit ZIP) and the action (extract and summarize), and distinguishes itself from sibling tools that target WordPress/Cloudflare, as this is the only Ahrefs-specific 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 provides clear context for when to use the tool: when handling an Ahrefs site audit ZIP file. It does not explicitly mention alternatives or exclusions, but since siblings are unrelated (wp_*, cloudflare_*), there is no ambiguity about which tool to choose for this task.

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 list expected return outputs, which adds value, but it does not explicitly state that the operation is read-only, nor does it cover error behavior, rate limits, or permission requirements beyond the schema. The tool name 'check' implies non-destructive behavior, but an explicit statement would be stronger for a no-annotation 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?

The description is a single, front-loaded sentence that names the action and resource, then lists return items. Every word carries weight; there is no fluff or repetition. This is exemplary conciseness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple check tool with three well-documented parameters and no output schema, the description adequately explains the return value categories and recommendations. However, it could be more complete by explicitly noting the read-only nature and when to pair it with cloudflare_fix. The overall structure is solid, but minor gaps prevent a perfect score.

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 schema already documents each parameter (email, api_key, zone_id) clearly. The description adds no further semantic meaning to the parameters, so the baseline score of 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?

The description clearly states the tool checks CloudFlare security and performance settings for a zone, listing specific return items (SSL mode, TLS version, HSTS status, bot protection). This is specific and understandable, but it does not explicitly distinguish itself from the sibling tool cloudflare_fix, so it misses the top score.

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 guidance is provided on when to use this tool versus alternatives like cloudflare_fix. The description does not mention exclusions, prerequisites, or scenarios where another tool would be more appropriate. This leaves the agent without decision support.

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 burden. It discloses a meaningful behavioral trait: 'By default, checks current settings and only fixes what's needed.' This is useful for agents to predict incremental behavior. However, it does not mention side effects, reversibility, API key permissions, or return values, which are relevant for a mutation tool.

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 two sentences, front-loaded with the primary purpose, and free of redundancy. It communicates the core action and key default behavior without wasted words.

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 (8 parameters, no output schema, no annotations), the description provides a good high-level overview and default behavior, but lacks details about what the function returns, potential side effects, or success/failure indicators. This is adequate but not comprehensive.

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 baseline is 3. The description doesn't add significant meaning beyond the schema; the list of fix targets (SSL, TLS, HSTS, bots) mirrors the parameter descriptions, and the default behavior is already encoded in the schema descriptions. The description adds minimal extra 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 it applies recommended CloudFlare security settings, enumerates the specific fixes (SSL mode, TLS version, HSTS, bot protection), and implicitly distinguishes itself from the sibling cloudflare_check tool by focusing on applying fixes rather than checking.

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 gives a clear use case ('Apply recommended CloudFlare security settings') and explains the default behavior of checking before fixing. However, it does not explicitly state when to use this tool instead of cloudflare_check or provide exclusion scenarios, leaving some ambiguity.

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 discloses the tool's behavior by listing the output categories (content counts, database size, etc.), implying a read-only audit. However, it does not explicitly state that it makes no changes, nor does it mention performance implications or permissions, which leaves some ambiguity for a comprehensive audit tool.

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 a single sentence that front-loads the primary action and then enumerates the key return categories in a comma-separated list. There is no wasted wording, and the structure makes it easy to scan.

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?

This is a fairly complex audit tool with no output schema, so the description must compensate by explaining return values. It lists six major categories, which gives a solid conceptual overview. However, it lacks detail on the structure or format of the returns and does not mention potential side effects or performance considerations, leaving some gaps for a tool of this scope.

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 provides a complete description of the single parameter (site_id as 'WP Engine environment name'), achieving 100% schema coverage. The description adds no additional parameter meaning, so the baseline score of 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?

The description clearly states the tool runs a comprehensive baseline audit on a WordPress site, with a specific verb and resource. It lists six distinct return categories, which distinguishes it from sibling tools like wp_seo_check or wp_plugin_artifacts that focus on narrower 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?

The description implies usage as a broad audit for getting an overview, but it does not explicitly state when to use this instead of the more specific sibling tools, nor does it mention any exclusions or prerequisites. The context is present but not fully explicit, so it earns a 3.

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 provided, the description carries the full burden. It explicitly lists destructive actions (removes orphaned postmeta, revisions, auto-drafts, etc.) and even includes 'closes pingbacks'. This is substantive disclosure, though it stops short of stating irreversibility or backup requirements.

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 a single, information-dense sentence. It front-loads the purpose and follows with a concise list of actions, with no unnecessary words.

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 covers the main behavior thoroughly for a 2-parameter tool with no output schema. It lacks details like thresholds for 'old' or output expectations, but given the scope, it is sufficiently complete.

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 both parameters are already well-documented. The description does not add extra parameter-level meaning, but the baseline is 3, which 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 runs database cleanup on a WordPress site and enumerates specific items removed (orphaned postmeta/termmeta, revisions, auto-drafts, etc.). This differentiates it from sibling tools like wp_clear_cache or wp_seo_check.

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 clear context for when to use the tool ('Run database cleanup'), implying it is for database maintenance issues. However, it does not explicitly mention alternatives or when not to use it, though sibling tool names are visible.

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 provided, the description carries full responsibility for behavioral disclosure. It transparently lists what will be cleared, indicating a mutating/destructive operation, but does not mention prerequisites like admin credentials or potential side effects such as temporary performance impact. The enumeration of affected caches adds value but leaves some behavioral gaps.

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 a single, information-dense sentence listing all affected cache types without redundancy or unnecessary words. Every element earns its place, maximizing clarity in minimal 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?

For a one-parameter tool with no output schema, the description thoroughly explains what the tool does and which caches are affected. It lacks mention of side effects or post-condition, but for basic selection and invocation, the scope of behavior is well covered.

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%—the only parameter, site_id, is already described as 'WP Engine environment name' in the schema. The description adds no additional parameter meaning, so it meets the baseline but does not exceed it.

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 uses specific verb 'Clear' with resource 'all caches on a WordPress site' and enumerates cache types (WP object cache, transients, WP Rocket, Elementor, Beaver Builder, WP Engine), distinguishing it clearly from sibling tools like wp_rocket_fix or cloudflare_fix. This is 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 clearly implies this is the comprehensive cache clearing tool by listing all cache types, providing strong context for when to use it. It does not explicitly name alternatives or exclusions, but the scope of 'all caches' guides selection appropriately.

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 must carry the full burden. It explicitly states the action is 'remove' which implies destructive behavior, and specifies the affected data (tables and options). However, it does not mention irreversibility, permissions, or the availability of dry_run, which is important for a destructive tool. This is a moderate gap in transparency.

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 two sentences, front-loaded with the core function and followed by a necessary list of supported plugins. Every word is useful, no fluff or 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 description plus schema cover the tool's purpose, parameters, and supported plugins. Without an output schema, return values are not described, but this is not critical for a cleanup tool. The main gap is the lack of explicit safety/usage context (e.g., when to dry_run, warnings about deletion), which could be improved but is not essential for basic 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 100%, so all parameters (site_id, plugins, dry_run) are already described in the schema. The description does not add semantic meaning beyond what the schema provides, only listing supported plugins which is also present in the plugins parameter description. 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?

The description clearly states it removes database artifacts (tables and options) left behind by deleted plugins. This specific verb+resource combination clearly differentiates it from siblings like wp_cleanup or wp_baseline, making the purpose 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 implies the tool is for cleaning up after deleted plugins, and lists supported plugins. While it does not explicitly name alternatives or exclusions, the context is clear enough for an agent to infer when to use this tool. A slight lack of explicit 'when-not-to-use' guidance prevents 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 provided, the description must carry the burden of disclosing behavior. It does state that it enables four specific settings, which is meaningful. However, it does not disclose potential side effects, reversibility, or the existence of a dry-run mode that is present in the schema but not highlighted for safety.

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 two concise sentences, front-loaded with the clear purpose ('Check and fix WP Rocket settings') followed by a specific list of enabled features. Every word earns its place with no filler or repetition.

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 simpler tool with two parameters and no output schema, the description covers the core function but lacks usage scenarios, side effects, and return-value information. Given the absence of annotations and the presence of sibling tools with overlapping purposes, more contextual detail would improve completeness.

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 baseline is 3. The description adds context about which settings are affected, but it does not explain the two parameters (site_id and dry_run) beyond what the schema already states. No additional parameter-level meaning is provided.

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 uses a specific verb+resource pair ('Check and fix WP Rocket settings') and enumerates the exact features it enables (cache preload, sitemap preload, lazy loading, mobile cache). This clearly distinguishes it from sibling tools like wp_seo_fix and cloudflare_fix, which target different systems.

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 usage is appropriate when WP Rocket settings need to be checked or fixed, but it does not explicitly state when to use it over alternatives or provide exclusions. Sibling tools like wp_cleanup and wp_clear_cache are not mentioned, so guidance is only implicit.

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 clearly communicates the read-only nature through 'Check' and 'Returns', and adds scope details ('all published pages and posts') and output type ('list of content missing meta descriptions'). It does not discuss side effects, but the wording implies none.

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 concise sentences, front-loaded with the primary action and ending with the output. No filler or redundant 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?

For a simple read-only check with only two params and no output schema, the description is sufficient. It covers purpose, scope, and output. Missing info like return format or edge cases is not critical for this tool class.

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 baseline is 3. The description adds context around 'all published pages and posts' which aligns with the post_type parameter, but does not provide new parameter-level detail beyond what is already in 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?

Uses a specific verb 'Check' with a clear resource 'SEO meta description status' and scope 'all published pages and posts'. Clearly distinguishes from sibling wp_seo_fix, which implies fixing rather than checking.

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 states what it does (checks status) and what it returns (list of missing meta descriptions), making it clear this is a diagnostic tool. It does not explicitly name alternatives, but the scope and output strongly imply when to use it versus tools like wp_seo_fix.

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 bears the transparency burden. 'Add' clearly indicates a write operation, and the two modes are disclosed. However, the dry_run parameter is not mentioned in the description—a notable gap since it controls whether changes are actually made. The description also doesn't state whether existing descriptions are overwritten or only missing ones. This makes it moderately transparent but not fully explicit.

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 a single, front-loaded sentence with a clear verb and resource. Every phrase adds value—no filler or repetition. It efficiently conveys the core purpose and both operational modes, making it highly concise while remaining informative.

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 annotations and no output schema, the description must provide complete context. It covers the main actions but omits important behavioral details such as dry_run's effect, what happens to existing descriptions, and what the tool returns/outputs. Given the 5-parameter schema and nested object, the description is adequate but not complete—an agent would need to rely on the schema for dry_run semantics and still might miss side effects. A score of 3 reflects this 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%, with each parameter (mode, dry_run, site_id, post_type, descriptions) clearly documented in the schema itself. The description adds minimal extra meaning beyond summarizing the two modes. Since the schema carries the parameter detail, a baseline score of 3 is appropriate; the description does not meaningfully enrich parameter understanding.

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's function: 'Add meta descriptions to pages/posts.' It distinguishes itself from sibling tools like wp_seo_check by focusing on fixing (adding/updating) rather than checking. The two modes (auto-generate from content or set specific descriptions) further clarify its purpose.

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 when to use each mode: 'auto-generate from content' for bulk fixing, and 'set specific descriptions for specific post IDs' for targeted edits. It does not explicitly mention wp_seo_check as an alternative or provide exclusion criteria, but the mode breakdown gives practical usage context. Lacks explicit 'when not to use' guidance, so a 4 is appropriate.

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