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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It explicitly lists the actions the tool performs (detects, locates, estimates, reports) and implies a read-only inspection. While it doesn't mention potential side effects or network behavior, the 'inspect' framing is sufficiently transparent for this 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, well-structured sentence that front-loads the core purpose ('Inspect a website before scraping it') and then lists concrete outcomes. It is concise, with no filler or redundant content.

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 (one parameter) and there is an output schema, so the description doesn't need to detail return values. It covers the main behaviors and differentiates from siblings. However, it doesn't mention error handling or behavior for unresponsive sites, which could be relevant but is not critical given the output schema likely covers return structures.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and the description does not explicitly explain the 'url' parameter format. It implicitly associates 'website' with the URL, but it does not provide details like expected scheme (http/https) or whether the URL must be a full absolute URL. With only one parameter, this isn't a major gap, but the description adds minimal parameter-specific 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 tool's function with a specific verb ('Inspect'), a resource ('a website'), and detailed capabilities (detect platform, locate sitemap, estimate pages, report JS rendering). It distinguishes itself from sibling tools like fetch_page or crawl_site by focusing on pre-scraping analysis.

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 phrase 'before scraping it' gives clear contextual guidance on when to use this tool, implying it should precede scraping operations. However, it does not explicitly name alternatives or provide exclusion criteria, so it falls short of a full 5.

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

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

With no annotations, the description carries the full burden of behavioral disclosure. It does well by sharing the sitemap preference, sitemap index/robots.txt handling, fallback to link-following, and the exact JSON return fields including 'truncated.' It doesn't mention rate limits or site impact, but it covers the key behavioral aspects.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences with the main purpose front-loaded. Every sentence adds value: purpose, crawl strategy, return payload, and usage recommendation. No filler 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 gives a solid overview for a moderately complex crawler: discovery method, fallback behavior, and return fields. Since an output schema exists, return-value details are less critical. Minor gaps like limit semantics and edge cases (e.g., no sitemap) keep it from a 5.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and the description does not explain the 'url' or 'limit' parameters at all. The schema only provides titles and defaults, so the tool description fails to compensate for the missing parameter documentation.

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 opens with a clear, specific verb and resource: 'Discover the pages on a website.' It also distinguishes the tool from siblings by explicitly stating it should be run before fetch_pages to scrape a whole site, making its role in the workflow obvious.

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 clear usage context: run this before fetch_pages to scrape a whole site. It also explains the sitemap-first strategy and fallback behavior. It doesn't explicitly state when not to use it or name all alternative tools, so it stops short of a 5.

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

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

With no annotations, the description carries full behavioral disclosure. It reveals that the operation permanently removes stored rows and clarifies that scraped pages are unaffected, which are key side effects. It does not mention return behavior or potential errors, but for a delete operation this level of transparency is solid.

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 primary action and followed by a clarifying side-effect statement. Every word earns its place, 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?

This is a simple tool with one parameter and an output schema, so the description need not explain return values. It covers the core action, permanence, and non-effect on scraped pages, which is sufficient for an agent to use it correctly. The only gap is parameter description, but that is accounted for in parameter semantics.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, meaning the parameter 'name' has no description in the schema. The description does not explicitly describe the parameter; it only implies via 'Delete a saved result table' that 'name' identifies the table. This is minimal compensation for a low-coverage schema. A more explicit statement like 'name: the name of the table to delete' would be expected.

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 action: 'Delete a saved result table' with a specific verb (delete) and resource (result table). It also clarifies that it permanently removes rows but leaves scraped pages unaffected, which distinguishes it from other table-related tools like get_table, export_table, and query_table. This is a precise and unambiguous purpose statement.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context: it deletes a saved table and is permanent, implying use when a table is no longer needed. It does not explicitly mention alternatives or when not to use it, but the action is self-evident and the permanence note adds caution. Lacks explicit sibling differentiation but is adequate for an 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?

With no annotations, the description carries the full behavioral disclosure burden. It does state the core behaviors: writes a file in CSV or JSON and returns its path. However, it does not disclose side effects such as whether existing files are overwritten, how dest_dir is resolved, or any permission or error behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with the action, no filler. Every word adds value, and the purpose statement is immediately clear.

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, and an output schema exists, so return values are covered. However, the description omits parameter details and alternative usage guidance, leaving some context gaps for an agent deciding how to invoke it 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?

Schema description coverage is 0%, so the description must compensate, but it only hints at fmt via "CSV or JSON". The required parameter `name` is ambiguous (table name vs. output filename), and `dest_dir` is entirely unexplained. The description does not add enough meaning beyond the raw 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 uses a specific verb and resource: "Export a result table to a file on disk as CSV or JSON, and return its path." It clearly distinguishes this from sibling table tools like get_table or query_table, which return data rather than write it to disk.

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 phrase "Use this to hand data to a spreadsheet or another tool" provides clear usage context. It does not explicitly name alternatives or say when not to use it, but the intended use case is clearly communicated.

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 of behavioral disclosure. It explains key behaviors: resolving relative URLs to absolute, row_selector producing table rows, and save_as storing rows. However, it does not disclose potential side effects like whether it performs writes (e.g., saving to DB) or the exact behavior of js_render, leaving some ambiguity for a tool that could be both read and write.

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 dense but well-structured, offering essential details in three sentences with a clear logical flow: purpose, field mapping, row selection, attribute extraction, and storage. It uses inline code for parameters and a compact JSON example, earning its length without fluff. Slightly long but justified by the need to explain complex features.

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 complex (6 params, nested fields, output schema) and the description covers most usage aspects: selectors, attributes, row-based extraction, and save behavior. It omits details on js_render and exact return structure, but with an output schema present, that is acceptable. Overall, it provides sufficient guidance for effective use in a scraping workflow.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description must explain all parameters. It covers fields with an example, row_selector semantics, the @attr suffix, and save_as/mode usage. It does not explicitly describe urls (obvious) or js_render, but the core semantics are well-addressed, exceeding the baseline given the schema's lack of descriptions.

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 extracts arbitrary fields from pages using CSS selectors, positioning it as the general-purpose alternative to fixed extractors. It explicitly names the key parameters (fields, row_selector, save_as) and even provides a JSON example, making the tool's purpose unmistakable.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explicitly says this is 'the general case the fixed extractors do not cover', directly contrasting with sibling tools like extract_products and extract_links. It also gives concrete usage patterns: using row_selector for listings, attribute suffix for hrefs, and append mode for batching, which instructs when and how to apply the tool.

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 providing behavioral context, the description carries the full burden. It discloses that results can be returned inline or saved to a table via save_as, and that errors are included. However, it omits potential side effects like network usage, rate limits, or the meaning of mode/js_render, which limits full 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, extremely concise, and well-structured: it states the purpose, then the output format, then the save option. No extraneous information is present, and the structure is logical.

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?

While the tool's core function is clear, the description fails to provide sufficient context for optional parameters (mode, js_render) and does not elaborate on the output structure (e.g., what 'context' contains). Given the tool's moderate complexity, more detail is needed for full 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 coverage is 0%, so the description must explain parameters. It only clarifies save_as (storing vs returning) and implicitly urls (list of URLs). It leaves mode (what does 'replace' mean?) and js_render (when and why) unexplained, which is a significant gap given no parameter descriptions exist.

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 scans a list of URLs for email addresses, which is a specific verb-resource combination. It distinguishes itself from sibling tools like extract_phones and extract_social_links by focusing on emails, 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 clearly indicates when to use the tool (to extract emails from URLs) and mentions the save_as option for storing results instead of returning them. However, it does not explicitly contrast with alternatives, though the purpose is clear enough.

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 resolution to absolute URLs and the return format (results with url, value, context; errors), plus the save_as alternative. However, it does not mention side effects like page fetching behavior, handling of redirects, or limitations related to js_render and mode, which are important for behavioral 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?

Two sentences, front-loaded with purpose, then return format, then storage option. No redundant phrasing; every word serves a purpose.

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 core functionality and return format, but lacks detail on optional parameters (mode, js_render) and potential failure modes. Given the tool's complexity and existing output schema, it is acceptable 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 coverage is 0%, so the description must compensate. It explains save_as and implies urls, but leaves mode and js_render undefined. This is insufficient for a 4-parameter tool with zero schema descriptions.

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 collects every hyperlink from a list of URLs and resolves them to absolute URLs. This specific verb+resource scope distinguishes it from siblings like extract_social_links and extract_emails, which target different data types.

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 (provide URLs to extract hyperlinks) but does not explicitly mention when to use this tool over alternatives. It only notes the save_as option for storing results, leaving the decision of extraction type to the agent.

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 must carry the transparency burden. It discloses the return shape (results with url/value/context, errors) and the storage side effect of save_as, but it does not explain the meaning or impact of mode or js_render, nor any fetching/scraping implications.

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 purpose, and avoids redundancy. Every sentence adds meaningful information about behavior or output.

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 primary workflow, output schema expectations, and the save_as option, but it omits important parameter semantics and edge-case guidance. Given the 4-parameter schema and no annotations, this is adequate but not fully 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 0%, so the description must compensate. It explains save_as and implicitly urls, but mode and js_render are left entirely to their schema titles and defaults, which is insufficient for correct invocation.

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 and resource: 'Scan a list of URLs for phone numbers.' It clearly distinguishes this from sibling tools like extract_emails, extract_links, and fetch_page by naming the exact extraction target and input type.

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 you have a list of URLs and need phone numbers. It also explains the inline vs. save_as behavior, though it does not explicitly name alternatives or exclusions.

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

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

With no annotations, the description carries the burden. It discloses the method (reads JSON-LD/OpenGraph/microdata) and that it stores rows via save_as, which implies a side effect of saving data. However, it does not mention potential issues like rate limits, errors, or the effect of js_render, leaving gaps in behavioral disclosure.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences, front-loaded with the core purpose, and includes no fluff. Every clause adds value—specifying fields, method, compatibility, and save_as usage. It is concise and well-structured.

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 and presence of an output schema, the description covers the main behavior, method, and parameter for saving. However, it leaves out js_render entirely and does not mention any limits or edge cases, making it slightly incomplete. The output schema reduces the need to describe return values, but the missing parameter is a notable 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?

The description explains urls (list of product URLs) and save_as (stores rows for querying) but completely omits js_render. With schema coverage at 0%, this is insufficient. It adds some meaning beyond the schema but does not fully compensate for the unmentioned parameter, so a 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 specifies the action (extract structured product data) and the resource (list of product URLs), listing specific fields like name, price, currency, etc. It also distinguishes itself from siblings like extract_by_selector by explicitly noting it uses JSON-LD/OpenGraph/microdata instead of selector guessing, 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?

It states the tool 'works across most storefronts without configuration' and implies it is for structured product data, which helps decide when to use it. However, it does not explicitly state when not to use it or mention alternatives like extract_by_selector, though it contrasts with selector-based guessing. This provides context but lacks explicit exclusions.

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

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

With no annotations, the description carries full responsibility. It discloses the mechanism (reads products.json), the output structure (row per variant with listed fields), and behavior of parameters (save_as for storage, max_products for capping). It does not mention potential failure modes like missing products.json, but provides enough behavioral context for an agent to understand the tool's operation.

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: the first succinctly states the purpose and output format, the second explains the mechanism and key parameters. Every word earns its place, with no redundant or vague phrasing. It is front-loaded with the core action and concludes with practical guidance.

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 essential aspects: what it does, how it works, key parameters, and a storage recommendation. An output schema exists, so return values need not be detailed. It lacks explicit error-handling or limitations (e.g., stores without products.json), but for a Shopify-specific extractor, it provides sufficient context for typical usage.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description must explain all parameters. It does so effectively: store_url is implied as the store being extracted, save_as is explained as the table name for storage, and max_products is described as capping the number of products. All three parameters are given meaningful context beyond their names.

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 extracts a Shopify store's catalogue as one row per product variant, listing specific fields (price, sku, options, etc.). It distinguishes itself from siblings by mentioning it reads the public products.json and requires no rendering or selectors, which differentiates it from selector-based extraction tools like extract_by_selector and generic extract_products.

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 that it reads the store's public products.json, implying it works when that file is available. It also recommends using save_as for large catalogues, providing a practical usage tip. However, it does not explicitly state when not to use it or mention alternatives, though the context of Shopify-specific extraction 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?

With no annotations, the description carries the burden of disclosing behavior. It does mention the return format (JSON with results and errors) and the option to store results via save_as, but it does not disclose whether the tool performs network requests, any rate limits, or what happens on failure. It's basic but not deeply transparent.

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 reasonably concise, with two sentences that convey the core functionality and a key option. It could be more structured, but it's not verbose or padded.

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 (4 parameters, output schema present), the description covers the main purpose and output but lacks details on optional parameters (mode, js_render) and behavioral traits like error handling or rate limits. It's sufficient for a basic agent but incomplete for robust selection and invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, and the description only explains 'save_as' and 'urls' partially. It doesn't explain 'mode' or 'js_render' at all. The description fails to compensate for the lack of schema coverage, leaving agents uncertain about optional parameters.

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 extracts social media profile links from a list of URLs, listing the specific platforms supported. It distinguishes itself from sibling tools like extract_links, extract_emails, and extract_phones by focusing on social media profiles.

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 implicitly conveys when to use it: when you need social media links from URLs. However, there's no explicit when-not-to-use or comparison with alternatives like extract_links or extract_products. The sibling tools suggest possible overlap, but no exclusions are provided.

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 and delivers: automatic stripping of navigation/cookie banners/footers for articles, PDF extraction to text, actions implying js_render, and detailed behavior of each action type. This is thorough and goes beyond what annotations would typically provide.

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?

Every sentence earns its place. The description is front-loaded with the core purpose, then systematically covers parameters and actions. It is dense but not bloated, with a clean two-paragraph structure that separates basic usage from advanced 'actions' behavior.

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 (6 parameters, an actions array, multiple rendering modes), the description is remarkably complete. It covers all parameters, explains the actions schema, and provides practical example use cases. The output schema exists, so return values don't need explanation.

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 zero description coverage (only titles), so the tool description must compensate. It explains all parameters except the obvious 'url' — js_render, wait_ms, wait_for, main_content get clear usage context, and actions receives an entire paragraph with a complete list of action types and examples.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb 'Fetch' and clearly identifies the resource ('one web page') and the result ('clean markdown with metadata'). It distinguishes itself from sibling tools like fetch_pages (plural) and crawl_site by focusing on single-page retrieval with rendering options.

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 extensive guidance on when to use each parameter: js_render for SPAs/infinite-scroll, wait_for over fixed delays, main_content to control stripping, and actions for cookie gates/paginated listings. It lacks explicit mention of when not to use this tool vs alternatives, so it's not a 5.

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

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

With no annotations, the description carries the full burden. It discloses parallel fetching, return format (JSON with results and errors), optional JavaScript rendering, saving to a table, and the replace/append mode behavior. This covers the main behavioral traits. However, it does not mention potential side effects like whether saving to an existing table overwrites it (though mode explains this), nor rate limits or other constraints. Slightly more detail on error handling or table interactions would elevate it to 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?

The description is a single paragraph but flows logically: core purpose, then key option, then batching guidance. It is not overly verbose for the complexity involved, though it could be broken into bullet points for clarity. Every sentence adds value, but the length might be slightly long. Still, it is well-structured and 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 covers the major use cases: parallel fetch, JS-heavy pages, large URL batches via save_as, and batch replacement behavior. It also mentions the return format and follow-up with query_table. Given the tool's complexity (6 parameters, batching, parallel execution), it is complete enough for an agent to use effectively. The presence of an output schema (though not shown) and the description's hints at results/errors provide sufficient 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 0%, so the description is the sole source of parameter meaning. It explains js_render (for heavy JS), save_as (to write to a table), and mode (append vs replace). However, wait_ms and wait_for are not mentioned, and urls is self-explanatory. Since important parameters like batching are well explained but others are omitted, this is adequate but not comprehensive. A 3 reflects that it partially compensates for the missing schema descriptions.

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 'Fetch many web pages in parallel', specifying the action (fetch), resource (web pages), and the batch nature (many, parallel). This distinctly differentiates it from the sibling 'fetch_page' tool, which likely handles single pages. The verb 'fetch' is specific and the scope (many pages) is 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 rich usage guidance: when to set js_render for JavaScript-heavy pages, when to use save_as for >20 URLs to avoid filling the conversation, and the exact pattern for batching with mode='append'. It also references the complementary query_table tool for further interrogation. While it doesn't explicitly say 'use fetch_page for single pages', the name and context imply that, and the instructions cover the key scenarios for this tool.

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 provided, so description carries full burden. It discloses the data source (OpenStreetMap), the absence of ratings, and the optional save_as behavior. It doesn't mention any side effects of saving (e.g., creating a table), but the save_as parameter hint is present. Overall, good disclosure for a search 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?

Description is one long sentence but conveys all key points without fluff. It's front-loaded with purpose then examples. Could be split into clearer sentences, but effective. No 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 presence of an output schema (which presumably details return structure), the description covers essential usage and limitations well. It tells the agent what to expect (fields), warns about a key limitation, and hints at saving results. For a search tool with 3 params, this is complete enough.

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 has 3 params with 0% description coverage EchoParam, so description must compensate. It explains 'query' via examples alludes to it and explicitly documents 'save_as'. But 'limit' is not mentioned at all. So partial coverage.

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?

Clear verb+resource: 'Search for places and local businesses by name or description'. Includes concrete examples and lists return fields. Distinguishes from find_places_nearby (implicitly, by not focusing on proximity) and search_web.

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?

States the query pattern and explicitly warns about data source limitation (no ratings/reviews) and suggests paid Google Places for that need. Doesn't explicitly say when not to use compared to siblings like find_places_nearby, but the limitation note serves as a guide.

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

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

No annotations are provided, so the description carries the full behavioral burden. It discloses data source (OpenStreetMap), the absence of star ratings, returned fields, and the save_as storage side effect. It could mention rate limits or data availability, but it is reasonably transparent.

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?

Every sentence earns its place: purpose, examples, category syntax, data caveat, and save_as behavior. It is dense but not bloated, with no 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?

For a 5-parameter list-style tool with an output schema available, the description covers purpose, parameter semantics, output fields, and side effects. Minor gaps like limit semantics and explicit radius units are addressed by schema defaults and parameter naming.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description compensates by explaining category (friendly names vs. OSM tags), near (place names), radius, and save_as. Limit is not addressed, but the description adds substantial semantic value beyond the bare 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?

Clearly states it finds every business of a given category within a radius of a place, with concrete examples and expected return fields. The phrase 'This is the tool for local lead generation' helps distinguish it from the sibling find_places.

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 explicit use-case context ('dentists near Bath', 'cafes within 2km of Shoreditch', local lead generation). It does not explicitly name when-not-to-use or alternatives, but the context is clear enough to guide tool selection.

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 behavioral disclosure burden. It transparently states the tool's read-only inspection nature and enumerates the returned information (columns, row count, sample rows). It does not discuss error cases or prerequisites, but for a simple inspection tool this is 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 a single, front-loaded sentence with no filler or repetition. Every word contributes to explaining the tool's purpose and output.

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, has an output schema, and the description covers the core behavior and return contents. It does not explain prerequisites or edge cases, but the presence of an output schema and the low complexity make the description 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 0%, so the description must compensate for parameter meaning. It indirectly maps to the parameters: 'one result table' implies the `name` parameter, and 'a small sample of rows' implies `sample`. However, it does not explicitly name or explain either parameter, leaving some ambiguity.

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 ('Inspect') and resource ('one result table') and clearly enumerates what is returned: columns, row count, and a sample of rows. This distinguishes it from siblings like list_tables (listing all tables) and query_table (running queries).

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 phrase 'Inspect one result table' clearly conveys when to use this tool: when you need details about a single table rather than listing or querying tables. It does not explicitly name alternatives or exclusions, but the context is clear enough for an agent to differentiate it from sibling tools.

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

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

No annotations are provided, so the description carries the full burden. It discloses that the tool renders a page and inspects network calls, and mentions that include_types controls content type. However, it does not explain broader details such as whether this triggers side effects, how many requests are captured, how responses are truncated, or what the output structure contains.

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 and front-loaded with the core purpose before expanding on when and why to use this tool. Every sentence earns its place, including the rationale about cleanliness, cost, and resilience to redesigns.

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 provides a strong strategic context but lacks enough operational detail to fully guide an agent invoking this tool. Although the output schema reduces some need to describe return values, the six parameters are mostly undocumented, and there are no annotations to fill the gap. Important context like save_as behavior, wait_for semantics, and max_body_chars limits is 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?

The input schema has zero description coverage, so the description must compensate. It only explains one parameter, include_types ('widen beyond JSON'), and says nothing about the semantics or typical values of url, save_as, wait_ms, wait_for, or max_body_chars. The value added beyond schema is minimal.

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: 'Render a page and report the API calls it makes, with their JSON responses.' It uses a specific verb and resource combination and distinguishes itself from sibling tools like fetch_page and extract_by_selector by focusing on discovering network endpoints rather than fetching or parsing pages directly.

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 recommends using this tool 'when a page is hard to scrape' and suggests the follow-up action 'fetch the endpoint it reveals.' It contrasts the approach with parsing rendered markup, noting it is 'cleaner and far cheaper,' but it does not explicitly name alternative sibling tools for contrast.

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 of disclosure. It states the tool lists collections with counts but does not mention any side effects, authentication requirements, network behavior, or data format details. For a simple read operation, this is acceptable but minimal; it does not contradict annotations (none exist) and provides some context about output (product counts).

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, both purposeful: the first states what the tool does, the second gives usage guidance. There is zero wasteful text, and the structure is appropriately front-loaded with the core functionality.

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 (1 param, output schema exists) and the description covers basic purpose and usage. However, it does not explain the store_url parameter or any behavioral details like pagination or output shape, relying entirely on the output schema (not shown here). Given the tool's simplicity, this is adequate but not exceptional, missing some context that could help the agent use it 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?

The schema has 0% description coverage for the single parameter store_url, and the description does not explain it at all. The tool description only mentions 'a Shopify store's collections' but does not clarify the format, scheme, or required structure of store_url. Since the schema provides no guidance and the description adds no parameter-specific meaning, this is a significant gap.

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 lists a Shopify store's collections and includes product counts, which is specific and distinct from the sibling extract_shopify_store tool. It names the resource (collections) and the action (list) without 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 explicitly tells when to use this tool: 'Use this to pick which collections to extract before calling extract_shopify_store.' It gives a clear use case and directly references the alternative/extraction tool, leaving no doubt about its purpose in the workflow.

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

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

With no annotations, the description carries the behavioral disclosure burden. It states the provenance of tables (produced via save_as) and what the output includes (row counts and columns), implying a read-only listing operation with no 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?

Two short sentences pack the essential information: what is listed, what is included, and where tables come from. No filler 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?

Given that the tool has no parameters and an output schema exists for return values, the description fully covers the necessary context: what the tool does, what its output summarizes, and how result tables originate. No critical information 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 has zero parameters, so schema coverage is complete and there are no parameter meanings to clarify. The baseline of 4 applies because the description has no parameter burden to fulfill.

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 ('List') and names the exact resource ('saved result tables'), plus states the returned information (row counts and columns). It clearly distinguishes this tool from siblings like get_table, query_table, and drop_table.

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 that result tables are produced by any tool called with save_as, giving clear context for when saved tables exist and when this listing tool is relevant. It does not explicitly name alternatives or exclusions, but for a zero-parameter list operation this is sufficient.

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 stand alone. It says 'List the pages being tracked' which implies a read-only operation, but it doesn't explicitly state that it doesn't modify data or mention any side effects. For a simple list operation, this is acceptable but minimal.

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, front-loaded with the action and resource, and includes relevant details like 'with when each was last seen'. 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?

Given that it's a simple list operation with no parameters and an output schema provided, the description is sufficient. It clearly states what it returns (pages and last-seen times). It doesn't mention any limitations or relationships to other tools, but for a straightforward list, this is adequate.

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, so the description doesn't need to explain any. It correctly reflects that no input is required.

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 (

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 states the purpose (listing tracked pages) but does not explicitly mention when to use it over alternatives or any preconditions. It's clear enough that this is the tool to check currently tracked pages, but lacks explicit exclusion 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?

With no annotations provided, the description carries the full burden and does an excellent job: it declares read-only behavior, states that only SELECT is permitted, clarifies the query can never modify saved data, and explains that original data remains untouched unless the save_as name deliberately targets the original table.

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: the main purpose and safety context come first, followed by a realistic example and a practical save_as workflow. It is slightly longer than necessary due to some restatement of safety guarantees, but every key concept contributes meaningfully.

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 is strong for primary behavior and saving results, but it leaves out the max_rows semantic, which is important for agents deciding whether they will receive all matching rows or only a capped page. Given an output schema exists, return values are not needed, but the parameter gap prevents this from being fully 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?

The description gives strong, concrete meaning to sql and save_as through an example and workflow explanation. However, schema description coverage is 0% and max_rows is never mentioned, so the 200-row default limit and its impact on returned output are left undocumented.

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 action, 'Run a read-only SQL SELECT', and names the exact resource, 'saved result tables'. It distinguishes itself from extraction and export siblings by focusing on in-place analysis with filters, aggregation, and grouping, and it explicitly says it is how you analyse a large scrape.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It clearly states when to use it: when you need to analyse a large scrape without pulling all data into the conversation. It also gives a clear workflow for saving cleaned results with save_as. However, it does not explicitly name alternative tools like get_table or list_tables for cases where this tool is not the right fit.

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 behavioral disclosure burden. It discloses the output shape (ranked results with titles, URLs, snippets) and access characteristics (no API key, no quota), which is helpful. However, it does not explain the behavior of the save_as parameter, limit handling, or any potential side effects such as saving results locally.

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 with no filler. It front-loads the core action and result format, then adds workflow guidance and access constraints, making every sentence earn 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?

The tool is simple with only one required parameter and an output schema, so the description covers the main usage scenario well. However, the unexplained save_as parameter and lack of any annotation leave a gap in understanding the full side effects and input semantics, making it not fully 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 0%, so the description must compensate for parameter meaning, but it does not explain limit or save_as explicitly. The query parameter is loosely implied by 'a question', but the other two parameters rely entirely on their names and defaults for inference. This leaves meaningful ambiguity, especially for save_as.

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 performs web searches and returns ranked results with titles, URLs, and snippets. It explicitly positions the tool as the entry point for question-based lookups rather than URL-based processing, which distinguishes it from sibling tools like fetch_pages and extract_by_selector.

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 strong usage context: use it when you have a question rather than a URL, and then feed resulting URLs into fetch_pages or extract_by_selector. It does not enumerate alternative search tools or explicitly state when not to use it, but the guidance 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?

With no annotations available, the description carries the behavioral transparency burden and does a good job: it discloses the stateful 'since the last time it was checked' behavior, the possible status values, unified diff output, line counts, and that this is not scheduled. It could add more detail about storage or rate limits, but it is still substantially transparent.

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 long, front-loads the core action, and every sentence adds value. It avoids repetition and boilerplate while still giving examples and return behavior.

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 is fairly complete for a moderately stateful tool: it explains what the tool does, what it returns, and when to use it. The main gap is parameter semantics, but since an output schema exists and the core lifecycle is described, the overall context is sufficient for most monitoring use cases.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, and the description does not explain js_render or context_lines at all. The URL parameter is implied by 'Fetch a page', but the boolean rendering flag and diff context setting are left unexplained, so an agent cannot confidently tune those parameters.

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 action ('Fetch a page and report what changed since the last time it was checked') and clearly differentiates from sibling tools by emphasizing comparison, diff output, and monitoring statuses. Concrete use cases like price, job board, and policy page make the purpose immediately understandable.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It says this is 'monitoring without a scheduler' and gives examples of when to use it, which provides clear usage context. However, it does not explicitly contrast with sibling tools such as fetch_page or search_web, nor does it mention exclusions or when not to use it.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions that the stored snapshot is forgotten, which is useful, but it does not disclose whether this is destructive (irreversible), whether it affects other tracked data, or any side effects. The description is minimal and leaves the agent guessing about the consequences.

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, concise sentence that is front-loaded with the main action. It is efficient and to the point, though it could be slightly more informative without becoming verbose.

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 (one parameter, no annotations, no output schema details), the description is somewhat adequate but lacks important context. It does not explain the effect on the snapshot, whether the action is reversible, or any related tools. The description is too sparse to fully guide an agent, especially without annotations.

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 schema has 0% description coverage, and the description does not explain the 'url' parameter beyond its name. The description implies the URL identifies the page to untrack, but it does not clarify format, validation, or behavior for invalid URLs. The description adds minimal value over 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 clearly states the action (stop tracking) and the resource (a page), and it adds the detail about forgetting the stored snapshot, which distinguishes it from simply pausing or disabling tracking. It is specific enough to differentiate from sibling tools like track_changes and list_tracked.

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 does not provide any guidance on when to use this tool versus alternatives, nor does it mention any prerequisites or conditions. It implies usage (when you want to stop tracking a page) but lacks explicit context or exclusions.

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