Server Quality Checklist

Tool Scores

• upshift_template_matchA
  4.5/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true and openWorldHint=false. The description adds behavioral context: it operates from a server-held catalog, makes no network call, and returns no matches (rather than forced) for out-of-scope trades. This reinforces and complements the annotations without contradiction.

  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 concise and front-loaded, consisting of three sentences that efficiently convey purpose, usage, and limitations without redundancy. Every sentence adds value.

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

  Completeness5/5

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

  Given that there is an output schema (the context indicates 'Has output schema: true'), the description does not need to detail return values. It adequately covers the tool's purpose, usage context, limitations (no forced matches), and the fact that it uses a local catalog. For a tool with two well-documented parameters and a closed set of templates, this is fully complete.

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

  Parameters4/5

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

  Schema description coverage is 100% with both parameters documented. The description adds meaning by explaining that 'industry' is the trade and 'needs' is optional, and it describes the output parameters (demo link, store link, prices, match words). This provides additional context beyond the schema's property descriptions.

  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 states the verb 'rank' and the resource 'Upshift's 14 website template lines'. It specifies the output (best three with demo link, store link, prices, match words) and distinguishes from sibling tools like site_audit and quote which serve different purposes.

  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 explicitly says 'Use when someone asks what a website for a given trade should look like or cost.' It also notes that it returns no matches for trades outside the 14 lines, providing context for when the tool is appropriate. However, it does not explicitly mention when not to use it or alternatives, though siblings are different enough that exclusion is implied.

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

• upshift_quoteA
  4.6/5.0
  Behavior4/5

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

  The description adds substantial behavioral context beyond the annotations. It reveals that the tool is deterministic ('same arguments always return the same answer'), makes no network call, and generates prices from a live store catalog. The annotations already declare readOnlyHint=true and openWorldHint=false, which the description aligns with. The only minor gap is not expanding on what the return structure looks like, but the tool has an output schema which mitigates this.

  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 paragraph of four sentences with clear front-loading: the first sentence states the core purpose. Each sentence adds distinct information. It could be slightly more structured (e.g., breaking guidelines into a separate sentence), but it's efficient and avoids waste.

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

  Completeness5/5

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

  Given the tool has only 2 parameters (1 required), an output schema, and readOnlyHint+openWorldHint annotations, the description is complete. It covers purpose, when to use, constraints (no network call, deterministic), and parameter semantics. The output schema covers return structure. There are no gaps in information needed for an agent to correctly select and invoke this tool.

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

  Parameters4/5

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

  Schema description coverage is 100%, so the baseline is 3. The description goes further by explaining what values each enum choice covers (e.g., 'mcp' includes registry listing, live tool preview, etc.) and explains the scope parameter's purpose (free text to help pick a tier, never changes prices). This adds genuine value beyond the schema's minimal descriptions.

  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 uses the specific verb 'Return' with the resource 'Upshift's real prices' and clearly distinguishes between two job types (mcp and website). It immediately communicates that this tool provides actual listed prices, not estimates, and gives concrete examples of what each job_type covers, making it easy for an agent to understand exactly what this tool does.

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

  Usage Guidelines5/5

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

  The description explicitly states when to use the tool: 'Use when someone asks what a job costs, what a tier includes, or how long it takes.' It also specifies limitations: it cannot quote a price that is not sold, and the same arguments always return the same answer. While it doesn't explicitly name sibling tools as alternatives, the context of pricing guidance is clearly delineated from other tools like upshift_site_audit.

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

• upshift_site_auditA
  4.9/5.0
  Behavior5/5

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

  Annotations include readOnlyHint and openWorldHint, but the description adds significant context: makes one outbound request, only sees what fetch can establish, refuses private/loopback/link-local addresses, and reports unreachable pages rather than scoring error bodies. This exceeds annotation coverage and provides critical behavioral details.

  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 concise, front-loaded with the core purpose and key features, each sentence adding new information: checklist, score, one outbound request, security restrictions, and unreachable behavior. No fluff or repetition.

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

  Completeness5/5

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

  For a single-parameter tool with output schema, the description covers purpose, usage, behavior, and security constraints comprehensively. It details limitations (no rendering) and edge cases (unreachable pages), making it complete for the agent to know what to expect.

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

  Parameters4/5

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

  Schema description coverage is 100% with clear description for url, so the baseline is 3. However, the description adds value by specifying the URL must be absolute http(s) and gives an example, as well as implying constraints (real site, public address), compensating slightly above baseline.

  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 states the tool audits a website for machine legibility, listing specific checks (JSON-LD, llms.txt, etc.) and outputs a 0-100 score. It distinguishes from siblings by mentioning auditing a live site, which is unique among upshift_template_match and upshift_quote.

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

  Usage Guidelines5/5

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

  Explicitly instructs to use this tool to check a real site before recommending changes, which contrasts with the sibling tools' likely non-audit purposes. It also explains when it's appropriate (real site) and what it does not do (no rendering or browser metrics), providing clear context for selection.

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