Server Quality Checklist

Tool Scores

• extract_data_from_urlB
  3.2/5.0
  Behavior2/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It only states the core fetch-and-extract behavior and does not mention limitations such as JavaScript rendering, selector failure handling, page-load behavior, rate limits, or whether the operation is safe and read-only.

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

  Conciseness4/5

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

  The description is a single, tight, front-loaded sentence with no wasted words. It communicates the core action and differentiator efficiently, though its brevity means it omits useful parameter and behavioral details that the low schema coverage cannot supply.

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

  Completeness2/5

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

  With no output schema and three inputs, the description is under-specified for safely invoking this tool. An agent is left without information about the return shape, error behavior, or how this tool relates to the sibling tools, which is a notable gap for a network-fetching and DOM-extraction tool.

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

  Parameters2/5

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

  Schema description coverage is only 33%, and the main description adds little beyond the schema's structural requirements. It does not explain how selectors map to returned values, what 'name' represents, how 'multiple' changes results, or how 'max_value_length' truncates data, leaving the agent to infer this from the schema alone.

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

  Purpose5/5

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

  The description states a specific action ('Fetches a web page and extracts precise data'), a clear resource ('web page'), and a specific method ('using CSS selectors'). It differentiates from sibling tools like extract_page_text and inspect_page_structure by emphasizing precise, selector-based extraction.

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

  Usage Guidelines3/5

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

  The description implies when to use the tool: when precise, selector-based data extraction from a page's DOM is needed. However, it does not explicitly state when to prefer this over siblings like extract_page_text or discover_selectors, nor does it mention any exclusions or conditions.

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

• extract_page_textB
  3.3/5.0
  Behavior3/5

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

  With no annotations, the description carries the full burden; it establishes that the tool performs a fetch and returns extracted text, suggesting a read operation. It does not disclose potential side effects like network calls and rate limits, or behavior such as truncation via max_length and errors on non-HTML pages, so transparency is only partially adequate.

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

  Conciseness5/5

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

  The description is a single tight sentence with the primary action front-loaded and the optional modifier at the end. There is no redundancy or filler; every word contributes to understanding the tool.

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

  Completeness3/5

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

  For a simple 3-parameter read tool the description covers the core flow, but it omits what `max_length` actually limits and does not mention error behavior or output format. Since there is no output schema or annotations, these gaps make the definition only minimally complete.

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

  Parameters2/5

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

  Schema description coverage is only 33%, and the tool description adds little beyond it: it echoes the selector scoping and frames `url` as the page to fetch, but leaves `max_length` semantically unexplained. The description does not compensate for the schema gaps for two of the three parameters.

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

  Purpose4/5

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

  The description gives a specific verb ('Fetches') and resource ('a web page'), and names the output ('readable text') plus an optional CSS selector scope. It clearly points to extracting page text rather than structured data or DOM structure, though it does not explicitly reference sibling tools.

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

  Usage Guidelines3/5

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

  The described behavior implies the main use case—reading text from a page, optionally focused via selector—but gives no explicit guidance on when to prefer this over extract_data_from_url, inspect_page_structure, discover_selectors, or probe_selectors. There are no when-not-to-use conditions or alternative routing, so the agent must infer placement.

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

• probe_selectorsA
  3.5/5.0
  Behavior3/5

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

  With no annotations, the description carries the full burden. It explains the basic behavior and output shape (match counts and a sample of the first match), but it does not disclose potential fetch failures, dynamic content limitations, or whether the operation is purely read-only. This is adequate but not rich.

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

  Conciseness5/5

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

  The description is two concise sentences with no wasted words. The primary action is front-loaded first, followed by a clear usage recommendation. It is appropriately sized for its purpose.

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

  Completeness3/5

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

  For a two-parameter tool with no output schema, the description gives a reasonable overview and states return behavior. However, it lacks details about the structure of the 'selectors' items, possible error behaviors, and how this tool relates to the sibling tools. It is minimally complete but leaves gaps an agent must infer.

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

  Parameters2/5

  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 the general role of selectors, but it never defines the required 'name'/'css' fields or the optional 'attribute' field, which the schema leaves only minimally documented. This is a notable gap.

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

  Purpose4/5

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

  The description clearly identifies the action ('Fetches a web page') and the resource ('for each CSS selector... how many elements match'), making the tool's core function easy to grasp. It does not explicitly contrast itself with sibling tools like discover_selectors or inspect_page_structure, so it falls short of a 5.

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

  Usage Guidelines4/5

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

  The phrase 'Use it to verify or refine candidate selectors cheaply' gives clear context for when the tool is appropriate. However, it does not mention when not to use it or name alternative tools, leaving some routing decision to the agent.

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

• inspect_page_structureA
  4/5.0
  Behavior3/5

  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 explains the main behavior (fetching and condensing the DOM), including notable aggregation of repeated siblings. However, it does not disclose possible failure modes, network effects, rendering behavior, or limits on page size/complexity, leaving some gaps for an online operation.

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

  Conciseness5/5

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

  The description is a single, front-loaded sentence that wastes no words. It states the action, the output, key structural features, and the practical purpose, making every phrase informative.

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

  Completeness4/5

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

  Given there is no output schema, the description reasonably explains what the tool returns and why it is useful. It would be stronger with a note about failure/error behavior or relationship to discover_selectors, but it otherwise gives an agent enough context to invoke the tool appropriately.

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

  Parameters3/5

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

  Schema description coverage is 67%: max_nodes and max_text_length have descriptions, while url relies on its format type. The tool description does not explicitly clarify parameter usage, but it implies 'url' via 'Fetches a web page' and gives context for size limits through 'condensed' and 'short text samples'. This is adequate but not especially enriching beyond the schema.

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

  Purpose5/5

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

  The description states a specific verb ('Fetches'), resource ('web page'), and output ('condensed structural outline of its DOM'), and connects it to the distinct goal of picking CSS selectors. This clearly separates it from siblings like extract_page_text, which would focus on textual content rather than structure.

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

  Usage Guidelines4/5

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

  'Lets the model pick relevant CSS selectors' gives a clear use context, and 'without loading the full page into context' provides a motivation for choosing it. It does not explicitly mention alternatives or when not to use it, but the context is sufficiently clear for an agent to make a reasonable choice among siblings.

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

• discover_selectorsA
  4.2/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the behavioral burden. It discloses that the page is fetched, only candidate selectors with short samples are returned, and the full page does not enter the context. It does not cover failure modes or auth, but the key behavior is well explained.

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

  Conciseness5/5

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

  Two tightly written sentences with no filler. The core function is front-loaded, and the behavioral caveat about context is placed second. Every clause earns its place.

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

  Completeness4/5

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

  For a three-parameter tool with no output schema, the description covers the inputs, the main behavior, and the output format (candidate selectors with short samples). It lacks only minor details like failure behavior, which are not essential for correct invocation.

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

  Parameters3/5

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

  Schema descriptions already cover targets and max_candidates (67% coverage), and url is self-explanatory. The tool description does not add parameter-specific meaning beyond what the schema already states, so it neither helps nor hurts.

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

  Purpose5/5

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

  The description states a specific action: fetch a web page and find CSS selectors for elements whose text matches given keywords. It clearly distinguishes this from sibling tools like extract_page_text and probe_selectors by describing the matching mechanism and the output shape.

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

  Usage Guidelines4/5

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

  The description conveys a clear use case: the model provides keywords and the server returns candidate selectors without loading the full page into context. This implies when to use it, but it does not explicitly name alternatives or state 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.