Server Quality Checklist

Tool Scores

• tepra_discoverA
  3.8/5.0
  Behavior3/5

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

  With no annotations, the description is the sole source of transparency. It reveals the network method (mDNS) and result (IP addresses), which is helpful. However, it does not disclose edge cases like no printers found, timeout behavior, or read-only nature. More detail would be beneficial.

  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, well-structured sentence with no filler. It is front-loaded with the action and target, 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.

  Completeness4/5

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

  For a simple tool with one optional parameter and no output schema, the description covers the primary behavior and return type (IP addresses). It does not explicitly state empty-result behavior or the exact return format, but the core use case is clear. Slightly more detail would make it 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?

  Schema coverage is 100% (timeoutMs is described in the schema), so the description needs no additional parameter information. It does not add value beyond the schema, hence the baseline score of 3.

  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 ('Search') with a clear target ('TEPRA printers on local network'), method ('mDNS'), and outcome ('return their IP addresses'). This clearly distinguishes it from sibling tools that operate on an already-discovered printer.

  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?

  Usage is implied by the purpose—use when you need to discover printer IPs—but the description does not explicitly state when to use this tool vs alternatives or mention prerequisites. No reference to siblings or a typical workflow is provided.

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

• tepra_statusA
  4/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full burden. It transparently states that the tool reports readiness and tape cartridge, implying a read-only status operation. However, it does not disclose edge-case behavior such as error handling or network requirements, so it is transparent but not exhaustive.

  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 sentence with no redundant words. It directly states the tool's purpose and is front-loaded with the key action and object.

  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 the tool's low complexity (one optional parameter, no nested objects, no output schema), the description adequately explains what the tool reports. It lacks exact return format details but is still complete enough for a simple status tool.

  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 schema fully describes the only parameter (Printer IP address, defaulting to the TEPRA_PRINTER_IP env var). The description adds no parameter information, so it remains at the baseline of 3 given high schema coverage.

  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 'Report' and names two concrete outputs: printer readiness and loaded tape cartridge. This clearly distinguishes it from sibling tools like tepra_discover, tepra_preview, and tepra_print, which serve different functions.

  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 explains what the tool does but gives no explicit guidance on when to use it versus alternatives. There is no mention of checking status before printing or when not to use it, so usage is only implied from the tool name and description.

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

• tepra_previewA
  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 transparency burden. It clearly discloses that the tool does not print and therefore does not consume tape, and that it returns an image. It could go further by detailing the exact return format, but it covers the most important side-effect distinction.

  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 exactly two sentences, front-loading the core action, output, and primary use case. Every word earns its place, with no redundancy or filler.

  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 the tool has 12 parameters but a rich schema, the description covers the essential behavior, the non-printing side effect, and the intended use case. The lack of an output schema means a more explicit return-format note would help, but the description is still largely complete for a preview tool.

  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 schema describes all 12 parameters with 100% coverage, so the description need not repeat parameter details. It correctly stays at the baseline of 3, adding no extra parameter-specific guidance beyond what the schema already provides.

  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 'Render' and identifies the resource 'a label', clearly stating the output is an image and the action is 'without printing'. This strongly distinguishes it from sibling tools like tepra_print.

  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 advises using the tool to 'check the layout before spending tape', providing clear context for when to call it. It does not name alternative tools, but the contrast with printing is implied, which is adequate for this tool.

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

• tepra_printA
  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 full burden. It discloses the most important behavioral trait: the tool consumes a physical resource (tape). It also warns to preview first if layout is uncertain, which is a significant side-effect disclosure. However, it doesn't mention potential errors, printer connectivity requirements, or whether the operation is blocking.

  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, concise sentence with no wasted words. It front-loads the purpose ('Render and print') and includes a critical caveat about tape consumption and preview guidance. Every word 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?

  Given the tool's complexity (14 params) and lack of output schema, the description provides essential context: purpose, resource consumption, and a preview recommendation. It could mention what happens on success/failure or how it interacts with printer discovery, but the core workflow is adequately covered. The schema handles parameter details, so the description remains appropriately scoped.

  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%, with each of the 14 parameters clearly described with types, defaults, and constraints. The tool description itself adds no parameter-specific meaning beyond this. Baseline of 3 is appropriate since the schema does the heavy lifting.

  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's function: 'Render and print a label on the TEPRA SR5900P.' It uses a specific verb ('render and print') and a specific resource (label on a named printer). This clearly distinguishes it from sibling tools like tepra_preview (preview only) and tepra_status (status check).

  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 gives clear usage context: 'Consumes tape — preview first if the layout is uncertain.' This implicitly recommends using the preview tool before printing and warns about the cost of misuse. While it doesn't explicitly exclude use cases, it provides a practical guideline for when to print vs. preview.

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