Server Quality Checklist

Tool Scores

• buildA
  3.7/5.0
  Behavior3/5

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

  The description discloses return values (success, compiler output, binary paths, flash/RAM usage) and notes that it may run configuration ('Configure (if needed)'). However, it does not mention side effects like creating build artifacts, cleaning behavior of the 'clean' parameter, or whether it modifies project files. With no annotations provided, the description carries the full burden and falls short of 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.

  Conciseness5/5

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

  The description is two sentences long, front-loaded with the action and toolchain, and every clause adds information. It efficiently covers purpose and output without repetition or fluff.

  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 build tool with three parameters and no output schema, the description plus schema provides adequate context. It explains what the tool returns (which is otherwise unknown) and that configuration may occur. Missing parameter explanations are the main gap, but the overall tool complexity is low enough that an agent can likely invoke it correctly.

  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 by explaining parameters, but it does not. 'clean', 'build_dir', and 'project_dir' are not described. While the tool's purpose gives some context, the description does not add meaning to these parameters beyond their names and defaults in 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 clearly states the tool's function: 'Configure (if needed) and build an STM32C011 project with CMake+Ninja+arm-none-eabi-gcc.' It provides a specific verb (build), a resource (STM32C011 project), and the toolchain, distinguishing it from siblings like scaffold_project, flash, and list_probes.

  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 usage when a compiled project is needed, but it does not explicitly contrast with alternatives (e.g., 'use scaffold_project to create a project' or 'use flash to upload'). No when-not-to-use criteria are given. The purpose is clear enough for an agent to infer, but explicit guidance is absent.

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

• flashA
  3.8/5.0
  Behavior3/5

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

  With no annotations, the description must carry behavioral transparency on its own. It discloses the underlying tool (STM32_Programmer_CLI) and the flashing mechanism, but does not mention side effects like erasing existing firmware, verification behavior, or failure modes. This is a moderate disclosure.

  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 sentences: the first delivers the core functionality, the second adds a practical tip about probe selection. No redundant words.

  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?

  The tool has no annotations and no output schema, so the description must provide complete operational context. It gives the target, interface, and tool, but omits prerequisites, output/return behavior, and how to discover serial numbers (e.g., via list_probes). It is adequate but not rich.

  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 coverage is 0%, so the description is the only source of parameter meaning. It explains serial_number's purpose and the accepted file extensions for file_path, but leaves erase, verify, reset_mode, frequency_khz, and part undocumented. This is insufficient for a 7-parameter tool.

  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 specifies the action (Flash), the target (STM32C011), the interface (SWD via ST-LINK), and the accepted file formats (.elf/.bin/.hex), distinguishing it from sibling tools like build and list_probes.

  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?

  It provides clear context that this tool is for flashing firmware to an STM32C011, and the serial_number tip addresses multi-probe environments. However, it does not explicitly state when to use it over alternatives or when not to use it, so it falls 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.

• list_probesA
  4.2/5.0
  Behavior3/5

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

  The description indicates a read-only listing action with 'List' and specifies that it returns serial numbers. However, with no annotations, the description carries the full burden for behavioral disclosure and doesn't explicitly state that it has no side effects or mention any prerequisites (e.g., ST-LINK drivers).

  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 redundant information. It is front-loaded with the action and resource.

  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 zero-parameter listing tool, the description is adequately complete: it states the purpose, the output (serial numbers), and the motivating scenario (multi-probe setups). It doesn't explain how the output integrates with sibling tools, but that's not essential for invoking this tool correctly.

  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?

  No parameters are defined, making schema coverage trivially 100%. The description adds no parameter details, but none are needed; the baseline for zero-parameter tools is high, and the description adds context about what the output contains.

  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 a specific verb ('List'), identifies the resource ('connected ST-LINK probes'), and adds key details ('serial numbers' and 'multi-probe setups'). This clearly distinguishes it from sibling tools like scaffold_project, build, and flash.

  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 'for multi-probe setups' provides clear context for when this tool is useful: when multiple debug probes are connected and identification is needed. It doesn't explicitly mention exclusions or alternatives, but given the sibling tools are unrelated actions, the usage intent is clear.

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

• scaffold_projectA
  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 key safety behavior: it will not overwrite a non-empty directory without force=True. It also states what files will be created. It does not mention side effects like permissions or success output, but the critical destructive behavior is covered.

  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 clean sentences: the first states the action and output, the second states the safety condition. No filler or repetition of schema defaults. Every word adds value.

  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 scaffolding tool with four parameters and no output schema, the description provides a concise list of artifacts and the overwrite rule. It does not describe the resulting directory hierarchy or the effects of project_name/part, but the core purpose and key edge case are sufficiently covered.

  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 0%, so the description must compensate. It explains project_dir as the target location and force as the overwrite toggle, but it does not clarify project_name or part (beyond the STM32C011 default). This partially bridges the gap but leaves half the parameters without additional semantic context.

  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 a specific verb ('Create') and names a precise resource ('minimal bare-metal CMake/Ninja STM32C011 project skeleton') with concrete contents (linker script, startup code, blinky main.c). This clearly distinguishes it from sibling tools (build, flash, list_probes) as the project-scaffolding operation.

  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 establishes the context (use when creating a new project skeleton) and includes an important usage condition ('Does not overwrite an existing non-empty directory unless force=True'). It does not explicitly name alternatives or exclusions, but the distinct scaffolding purpose and the sibling list make the intended use obvious.

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