Server Quality Checklist

Tool Scores

• extract_structured_dataC
  2.9/5.0
  Behavior2/5

  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, but it only states what is extracted and from where. It does not disclose that this likely performs a live network fetch, any side effects, permission or rate-limit considerations, or distinctions between the 'fast' and 'deep' modes in terms of behavior.

  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 focused sentence with no superfluous words. It leads with the main action and resources, making it efficient and easy to parse.

  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?

  For a tool with 9 parameters, nested objects, no output schema, and sibling tools to disambiguate, this one-sentence description is insufficiently complete. It omits usage guuidelines, behavioral expectations, and return-value structure, leaving meaningful gaps for an agent trying to invoke it correctly.

  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?

  The input schema covers all 9 parameters with detailed descriptions, including examples, so the baseline is 3. The description adds little beyond the schema: it lists example metadata fields (OG tags, canonical URL, author, dates) which clarifies output scope, but does not elaborate on parameter syntax or interplay.

  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 states a specific verb ('Extract') and resources ('page metadata', 'custom CSS selector JSON schema mapping'), making the tool's purpose understandable. It does not explicitly differentiate from sibling tools like extract_web_content or batch_extract_web_content, so it misses the top tier by a narrow margin.

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

  Usage Guidelines2/5

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

  No guidance is provided about when to use this tool versus the sibling tools extract_web_content or batch_extract_web_content. The description does not mention any conditions, alternatives, or exclusions, leaving the agent to infer usage entirely from names.

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

• extract_web_contentC
  2.9/5.0
  Behavior2/5

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

  With no annotations present, the description carries the full burden of behavioral disclosure. It only states the output is token-optimized clean Markdown; it does not reveal that the tool makes live network requests, that 'deep' mode executes JavaScript via a headless browser, how failures or rate limits are handled, or any side effects. The schema documents the mode options, but the description itself leaves key behavioral traits undisclosed.

  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, front-loaded sentence that communicates the primary purpose and output format without wasted words. It is appropriately concise, though a little more detail about usage trade-offs would have made it richer without harming structure.

  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?

  The tool has 7 parameters, nested objects, and no output schema or annotations, yet the description only covers the surface purpose. It omits important operational context such as dynamic content handling, proxy/cookie use cases, retry behavior, and how to decide between 'fast' and 'deep' modes. An agent receives the raw schema but not sufficient high-level orientation for a tool of this complexity.

  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 100%, so every parameter already has a clear description in the schema. The tool description adds little beyond 'clean Markdown', which indirectly hints at the purpose of css_selector scoping but does not meaningfully extend parameter understanding. Baseline 3 is appropriate because the schema does the heavy lifting.

  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 has a clear verb ('Extract'), a specific resource ('content from a target website'), and a defined output format ('clean Markdown content'). It conveys the tool's core purpose well and inherently contrasts with extract_structured_data by promising Markdown. However, it does not explicitly distinguish itself from batch_extract_web_content, leaving the single-URL versus batch distinction to be inferred from the sibling name.

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

  Usage Guidelines2/5

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

  No guidance is provided about when to use this tool versus its siblings. There is no mention of batch_extract_web_content for bulk jobs or extract_structured_data for non-Markdown outputs. The 'for LLM consumption' phrase gives some context but does not help an agent choose among alternatives.

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

• batch_extract_web_contentA
  3.6/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the behavioral disclosure burden. It does disclose concurrency, output format, and token statistics, which are genuinely useful. However, it does not mention failure behavior, retries, partial failures, rate limits, or what happens when a URL cannot be fetched.

  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, compact sentence that front-loads the core purpose, then adds concurrency and statistical output details. There is no filler, and every phrase adds distinguishing information.

  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 annotations and no output schema, the description must supply more contextual completeness. It gives the essential purpose and concurrency trait, but it omits output shape, retry/failure semantics, and any usage comparison to sibling tools. For an 8-parameter tool with 100% schema coverage, this is still not fully complete.

  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?

  The input schema has 100% parameter description coverage, so the schema already documents all parameters well. The description adds no parameter-specific meaning beyond stating that the tool works on multiple URLs; therefore the baseline 3 is appropriate.

  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 clearly identifies the action ('batch extract'), resource ('web content from multiple website URLs'), output format ('token-optimized Markdown'), and a distinctive trait ('concurrently with aggregate token statistics'). This distinguishes it from the likely single-URL sibling `extract_web_content` and from structured extraction (`extract_structured_data`).

  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 word 'batch' and phrase 'multiple website URLs' imply this tool is for multi-URL scenarios, which provides useful context. However, there is no explicit guidance about when to prefer this over `extract_web_content` or `extract_structured_data`, and no stated exclusion conditions.

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