Server Quality Checklist

Tool Scores

• rattus_heartbeatC
  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. It discloses the rate (~20 Hz) and duration, and that it uses an open serial port, but it does not explain potential side effects (e.g., robot motion from CMD_TWIST), error behavior, or the meaning of the velocity parameters. This is insufficient for a tool that may control hardware.

  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 sentence that efficiently conveys the core action, rate, duration, and an important prerequisite. It contains no fluff, but the inclusion of 'Phase 2.7 soak / link-up' is somewhat cryptic and could be considered specialized. Overall, it is concise and front-loaded, though not perfectly structured.

  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 4 parameters, no output schema, and no annotations, the description is minimal. It lacks details on the velocity parameters, expected return values, and broader workflow (e.g., needing serial_open first). The phrase 'Phase 2.7 soak / link-up' gives some context, but the tool is not fully described for an agent to invoke it safely.

  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?

  The schema covers 50% of parameters (periodMs and durationMs have descriptions). The description adds meaning to durationMs explicitly ('for durationMs') and periodMs implicitly via '~20 Hz', but completely omits explanations for vMmS and omegaMradS, which are velocity-related and critical for understanding the tool's effect. The description does not compensate for the uncovered 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 states the specific action 'Send CMD_TWIST heartbeats' and adds frequency '~20 Hz' and duration via 'durationMs'. It clearly conveys a distinct operation, but does not explicitly distinguish it from the sibling tool 'rattus_send_twist', which may also send CMD_TWIST commands. The inclusion of 'Phase 2.7 soak / link-up' hints at the purpose but is not a full differentiation.

  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?

  It provides a clear context ('Phase 2.7 soak / link-up') and a prerequisite ('Uses open serial port'). However, it does not specify when to use this tool instead of alternatives like 'rattus_send_twist' or mention exclusions. The usage is implied rather than explicitly guided.

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

• lib_searchA
  3.5/5.0
  Behavior2/5

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

  No annotations are provided, so the description must carry the full burden. It only states the search action, without disclosing whether it is read-only, what output format to expect, or any limitations (e.g., pagination, case sensitivity). For a search tool, this is a notable gap.

  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 filler. Every word contributes to understanding the tool's 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?

  The tool is simple with one parameter, and the schema covers the input well. However, without an output schema, the description should explain what the search returns, but it does not. This leaves a gap in completeness.

  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 provides 100% description coverage, including a clear example ('Servo or ArduinoJson'). The description adds no additional parameter context, so the baseline of 3 applies per the rubric.

  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 ('Search') with a clear resource ('Arduino Library Manager') and mechanism ('by query string'). It clearly distinguishes from siblings like lib_install and core_list, which perform different actions.

  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 the tool is for finding libraries by query, but provides no explicit guidance on when to use it versus alternatives like lib_install or core_list. There are no exclusions or context cues beyond the basic purpose.

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

• rattus_crc_self_testA
  3.5/5.0
  Behavior2/5

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

  With no annotations available, the description carries the full burden of behavioral disclosure. It mentions the expected check vector but does not explain what happens on success or failure, whether it produces output, or if it has any side effects. The behavior beyond the stated verification is opaque.

  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, efficient sentence that front-loads the core action (verify) and resource. It adds the expected vector in parentheses without unnecessary fluff. Every word contributes value.

  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?

  Given the tool's simplicity (no params, no output schema), the description is adequate but minimal. It clearly states the purpose and expected result, but does not explain how to interpret a failure or what the user should do next. For a self-test, this is acceptable but could be improved with a note about exit codes or response behavior.

  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?

  The tool has zero parameters, so the baseline is 4. The description appropriately includes the expected check vector, which is a hardcoded value and not a parameter. No parameter documentation is needed since there are none.

  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 verifies that host-side CRC-8/MAXIM matches firmware RattusUart, with an explicit expected check vector (0xA1). The verb 'verify' and the specific resource (CRC-8/MAXIM vs firmware) make the purpose unmistakable and distinct from 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 Guidelines2/5

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

  No guidance is provided on when to use this tool versus alternatives. It does not mention whether it should be run after flashing, before serial communication, or in conjunction with other tools. The description simply states what it does without any situational context.

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

• lib_installA
  3.6/5.0
  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 says 'Install' without explaining side effects such as downloading from the internet, modifying the local filesystem, or potential interactions with existing libraries. This is a significant gap for a mutation tool.

  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, clear sentence with no extraneous words. 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?

  For a simple tool with one well-documented parameter and no output schema, the description is nearly complete. However, it could mention that installation involves network access or that it manages the local library index, adding a bit more context for the agent.

  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 already provides full coverage of the single parameter ('libraries') with a description ('Library names as known to Library Manager'). The description's 'by name' adds no new information beyond what the schema provides, so the baseline score of 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 states the action ('Install'), the object ('one or more Arduino libraries'), and the source ('from Library Manager'). It distinguishes from sibling tools like core_install (which installs cores) and lib_search (which searches libraries).

  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 action and object: one should use this when they want to install libraries. However, there is no explicit guidance on when not to use it or mention of alternatives like core_install, leaving room for ambiguity in more complex scenarios.

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

• serial_closeA
  3.8/5.0
  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. It only says 'close the currently open serial port session' but does not disclose what happens if no session is open, whether data is flushed, or any side effects on pending operations.

  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, clear sentence with no filler or redundant information, making it appropriately concise and front-loaded.

  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 (no parameters, no annotation coverage, no output schema), the description adequately conveys the core function. It could mention error handling when no session is open, but for a simple close operation it is sufficiently 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?

  The tool has no parameters, so per the rubric the baseline is 4. The description doesn't need to explain parameter semantics because there are none.

  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 action ('Close') and the target resource ('the currently open serial port session'). It is specific and distinguishes itself from siblings as the inverse of serial_open.

  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 rather than explicit: you would call this after opening a session with serial_open. However, it doesn't state when not to use it or provide alternative tools, leaving the guidance inferred from context.

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

• core_installA
  3.9/5.0
  Behavior2/5

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

  No annotations are provided, so the description must disclose behavioral traits. It only says 'install' without noting that this is a mutating operation that downloads files, may require network access, or could overwrite existing cores. There is no mention of side effects, prerequisites, or error 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 sentence with examples, front-loaded with the verb+resource structure. It contains zero fluff and is appropriately sized for a one-parameter 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?

  The tool is simple (one parameter) and the schema covers the parameter fully. However, the description does not mention what happens after installation, whether it returns success/failure, or any side effects. It is adequate for basic understanding but leaves behavioral gaps for a mutating operation.

  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?

  The input schema already describes the single parameter platformId with the same examples. The description adds the human-readable board names (Uno, Portenta H7) to those examples, providing additional semantic mapping beyond the schema. This is a modest but real addition.

  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 ('install') and resource ('Arduino core/platform') with a clear scope ('by id'). It provides concrete examples (arduino:avr for Uno, arduino:mbed_portenta for Portenta H7) that distinguish it from sibling tools like lib_install (libraries) and core_list (listing cores).

  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 clearly implies when to use this tool: to install a core/platform by ID. It does not explicitly contrast it with alternatives such as lib_install for libraries or core_list for listing, but the context is unambiguous and sufficient for most cases.

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

• board_listA
  4/5.0
  Behavior3/5

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

  With no annotations, the description carries the burden of behavioral disclosure. It mentions 'when possible' for FQBN detection, hinting at best-effort behavior. However, it does not explain what 'alias-friendly' means, nor does it mention discovery behavior, timeout handling, or output format. This is minimal transparency beyond the tool's name.

  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 one efficient sentence, front-loaded with the main action ('List connected boards') and a useful qualifier ('with detected FQBN when possible'). The companion note is brief and earns its place by distinguishing it from list_ports. No fluff or redundancy.

  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 list tool with one optional parameter and no output schema, the description is fairly complete. It indicates the tool lists boards and attempts FQBN detection, and relates it to list_ports. The main gap is the undefined term 'alias-friendly' and lack of explicit mention of return value/edge cases, but overall it provides enough context for a low-complexity 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 single optional parameter (discoveryTimeout) with a clear description: 'Optional discovery timeout in seconds.' The tool description adds no further meaning about this parameter or how it affects behavior, so it stays at the baseline for 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 clearly states the tool's function: 'List connected boards with detected FQBN when possible.' It uses a specific verb ('list') and resource ('boards'), and adds a key qualifier about FQBN detection. It also differentiates from sibling tool list_ports by labeling itself as a companion, making its purpose distinct.

  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 provides context by calling it a 'companion to list_ports,' implying it serves a different but related purpose. However, it does not explicitly state when to use board_list versus list_ports, nor does it offer exclusions or conditions. This is clear context without explicit alternatives guidance.

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

• compileA
  4/5.0
  Behavior2/5

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

  No annotations are provided, so the description must carry the full burden. It only reveals that compilation doesn't upload, but omits other behaviors such as potential core installation, build artifact creation, or whether it can fail. This is insufficient for a tool with no structured safety hints.

  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, front-loaded with the action and key distinction, with no redundant information.

  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 rich schema and the tool's straightforward nature, the description covers the main use case and distinguishes from upload. It doesn't mention prerequisites like core installs, but the schema's parameter descriptions fill in some gaps. Overall, adequate but not exhaustive.

  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?

  The schema covers all 6 parameters with descriptions, and the description adds specific FQBN examples (arduino:avr:uno and arduino:mbed_portenta:envie_m7) that go beyond the generic schema example. This enriches parameter understanding.

  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 'Compile' and resource 'sketch for a board FQBN', and explicitly states 'without uploading,' which distinguishes it from the sibling 'upload' tool. This clearly defines the tool's function.

  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 concrete FQBN mappings for common boards, indicating when to use those values. However, it does not explicitly name alternative tools like 'upload' or state when to prefer compilation over uploading, so it has clear context but no formal exclusions.

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

• serial_readA
  4/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the full burden. It mentions the buffer cap (~64KB) and its rationale ('to protect agent context'), which is useful. However, it does not disclose whether data is cleared after reading, whether the operation blocks, or what happens when the buffer is empty. This is adequate but minimal for a read tool.

  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, front-loaded with the core purpose, and a second sentence explaining the buffer cap. No wasted words; every sentence 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?

  The tool is simple, with full schema coverage and no output schema required. The description covers the purpose and a key safety constraint. It lacks an explicit link to serial_open as a prerequisite, but the phrase 'open serial port' implies it. Overall, sufficiently complete 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 description coverage is 100% for both parameters (encoding and maxBytes), so the schema fully documents their meaning and constraints. The description adds no parameter-specific syntax or format details; the buffer cap note is relevant context but not necessary for parameter usage. This aligns with the baseline 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 verb and resource: 'Read buffered bytes from the open serial port.' This clearly distinguishes it from sibling tools like serial_write, serial_close, and serial_status, as it focuses on the read operation on an already-open port.

  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 'open serial port' implies a prerequisite (serial_open must be called before this tool), providing clear context. However, it does not explicitly mention exclusions or alternatives among the sibling tools, so it lacks the explicit 'when not to use' guidance that would earn a 5.

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

• serial_statusA
  4/5.0
  Behavior3/5

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

  No annotations are provided, so the description must stand alone. It clearly indicates a read-only status check, but does not disclose potential behavior such as whether it errors if no serial session exists or whether it consumes buffered data. The description is adequate but not deeply detailed.

  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 that front-loads the primary purpose. It is concise and avoids redundancy, with no unnecessary words.

  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 status tool with no parameters and no output schema, the description adequately conveys what is reported: whether a session is open and the number of buffered bytes. It does not explain error cases or return format details, but these are less critical for a straightforward status check. Overall, it is complete for the tool's simplicity.

  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?

  The tool has zero parameters, and the schema coverage is trivially 100%. The description does not need to explain parameters, and the baseline for 0 params is 4. No additional parameter semantics are needed.

  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 reports on serial session status and byte count, using a specific verb (report) and resource (serial session). It distinguishes from sibling tools like serial_open or serial_read by focusing on status rather than actions.

  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 for checking if a serial session is open and how much data is buffered, but it does not explicitly state when to use this versus alternatives like serial_read or serial_close. The context is clear but lacks explicit guidance or exclusions.

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

• serial_writeA
  4/5.0
  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 adds useful context: the port must be open and binary data should be hex/base64 encoded. However, it does not disclose failure modes, blocking behavior, or what happens if the port is closed, which is a significant gap for a mutation tool.

  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 front-loaded sentences with no filler. The first sentence states the main purpose, and the second provides a practical encoding tip. 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?

  For a simple two-parameter tool with no output schema, the description covers purpose, prerequisite (open port), and encoding guidance. It does not explain return values or error conditions, but the tool is simple enough that this omission is not critical.

  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?

  The schema fully describes both parameters, so baseline is 3. The description adds value by advising hex/base64 for binary UART frames, directly illuminating the 'encoding' parameter's intended usage beyond the enum list.

  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 action (write) and resource (open serial port), distinguishing it from siblings like serial_read and serial_close. The purpose is unambiguous and immediately understandable.

  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 the need for an open serial port and advises using hex/base64 for binary data, but it does not explicitly name alternatives or state when not to use this tool. Context is clear enough, but explicit exclusions are missing.

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

• serial_openA
  4.1/5.0
  Behavior4/5

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

  No annotations are provided, so the description carries full behavioral disclosure. It mentions the exclusive access mode and the requirement to close previous sessions, which are important behavioral traits. However, it does not detail error handling or exact return values, leaving some gaps.

  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, front-loaded with the core purpose, and every sentence adds value. No fluff or redundancy.

  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 output schema, so the description should explain return values or success indicators, but it does not. It also omits error conditions. For a simple tool, this is a notable gap, though the essential usage is 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 description coverage is 100%, so parameters are already well-documented. The description adds only the 'Ratchet UART' context to the default baud rate, which is minor. Baseline 3 is appropriate as the schema carries 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: 'Open a serial port exclusively for read/write.' This is a specific verb+resource combination that distinguishes it from sibling tools like serial_read, serial_write, and serial_close.

  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 provides a clear prerequisite: 'Close any previous session first.' It also indicates the default baud rate, giving context for typical use. However, it does not explicitly mention when not to use this tool or suggest alternatives, 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.

• core_listA
  4.2/5.0
  Behavior4/5

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

  No annotations are provided, so the description carries the full transparency burden. It clearly indicates a read-only listing operation with no side effects (by using the verb 'List'), and provides concrete examples of output format. It does not describe edge cases or deeper behavior, but for a simple parameterless list tool, the description sufficiently discloses what the tool does.

  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 directly states the action and resource, with relevant examples. Every word earns its place; there is 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?

  For a simple, parameterless list tool, the description is complete: it names the tool's purpose, gives output examples, and implies the return format. While it does not explicitly describe the output schema or return type, the examples suffice for an agent to understand expected results. Given the tool's simplicity, no further context is needed.

  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?

  The tool has zero parameters, so the baseline score is 4. The description correctly mentions no parameters, and there is no additional semantic burden beyond what the empty schema already conveys. It adds context by giving examples of typical output values, which is helpful.

  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 lists installed Arduino cores (platform packages) with specific examples (arduino:avr, arduino:mbed_portenta). It uses a specific verb ('List') and resource ('installed Arduino cores'), and the examples distinguish it from sibling tools like core_install (which installs cores) and board_list (which lists boards).

  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 – if you need to see installed cores, use this tool – but it does not explicitly state when to use it vs alternatives like core_install or board_list. There is no exclusion or alternative guidance, so the context is clear but not explicitly comparative.

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

• rattus_send_twistA
  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 frame structure (CMD_TWIST), integrity check (CRC-8/MAXIM), target (open serial port), and dependency on serial_open. However, it does not mention error behavior or return values, which would be richer context.

  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, dense sentence that efficiently conveys purpose, protocol, destination, and prerequisite. Every clause adds value with no repetition 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?

  The description gives the essential context: what frame is sent, how it is encoded, where it goes, and what must happen first. It does not explain response handling or side effects, but since there is no output schema, this is not a major gap. It is sufficiently complete for a focused serial command 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?

  Schema coverage is 100%, with clear descriptions for vMmS and omegaMradS (linear and angular velocities) as well as seq. The description does not add any parameter-level detail beyond what the schema provides, so the baseline of 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 states the tool packs a CMD_TWIST frame with CRC-8/MAXIM and writes it to the serial port, specifying the exact resource and action. It is distinguished from general serial_write by naming the specific command type and protocol.

  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 explicitly states a prerequisite: "Requires serial_open first", which gives clear context for when this tool can be used. It does not name alternatives directly, but the sibling context and the phrase "PC-masquerade" imply it is for sending twist commands, and serial_write is for raw writes.

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

• list_portsA
  4.3/5.0
  Behavior4/5

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

  With no annotations provided, the description must carry the burden of behavioral disclosure. 'List' implies a read-only operation, and the description faithfully states what is detected. No side effects or special behaviors are omitted, and the tool is simple enough that nothing more is needed.

  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, clear sentence that conveys all necessary information without any filler. It is front-loaded with the verb and resource, making it immediately understandable.

  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 zero-parameter, no-output-schema tool, the description fully covers what the tool does. There is no complexity to explain, and the context is unambiguous.

  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?

  The tool takes no parameters, and the input schema has zero properties. The description doesn't need to explain parameters because there are none; the baseline of 4 applies automatically.

  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 action ('List') and the resource ('serial ports detected by arduino-cli'), with concrete examples (USB adapters, Uno, Portenta). This distinguishes it from sibling tools like board_list or serial_open.

  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 you need to see available serial ports) but does not explicitly mention alternatives or when-not-to-use scenarios. For a simple list operation, this is adequate but not explicit.

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

• uploadA
  4.4/5.0
  Behavior3/5

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

  With no annotations, the description carries the burden of behavioral disclosure. It does mention an important limitation: 'upload does not accept --libraries,' and hints at the inputDir/buildPath relationship (skipping recompile). However, it does not describe side effects such as overwriting the board's flash or requiring the serial port to be free, which would be helpful for safe usage. The description offers partial transparency but leaves gaps.

  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. The first sentence is a clear, front-loaded purpose. The second sentence is a precise usage tip. There is no fluff or repetition; every word earns its place. This is an exemplar of concise, well-structured tool documentation.

  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 tool with 6 parameters and no output schema, the description adequately covers the essential context: the action, the required workflow (compile first), and a critical constraint. The schema itself documents most parameters. The description might have mentioned return values or error states, but given the tool's simplicity and the schema's strength, it is sufficiently complete for correct selection and invocation.

  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 coverage is high (83%), so the baseline is 3. The description adds value beyond the schema by explaining the purpose of 'inputDir' (pass the 'buildPath' from a prior compile) and clarifying that 'upload' does not take '--libraries'. This contextual information helps the agent understand parameter relationships and limitations, elevating the score 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's function: 'Upload a sketch to a board on a serial port.' This is a specific verb+resource combination that distinguishes it from siblings like 'compile' (which builds rather than uploads) and serial tools. It also introduces the key workflow relationship with 'compile', further differentiating it.

  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 provides explicit usage guidance: 'Prefer compile first with libraries/buildPath, then pass the same buildPath as inputDir (upload does not accept --libraries).' This tells the agent exactly when and how to use the tool, and even warns about a common pitfall (no --libraries parameter). This is far more than a vague recommendation.

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

• arduino_cli_versionA
  4.5/5.0
  Behavior4/5

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

  The description discloses that the tool checks availability and reports the version, which is the full behavioral scope. It also indicates this is a verification step, implying no side effects. Without annotations, this is adequate for a simple read-only command.

  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?

  It's a single sentence that states the action, the resource, and the recommended invocation order, with no unnecessary words.

  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 version-check tool with no params and no output schema, the description covers the purpose, usage context, and suggests placement in the workflow. This is complete for the tool's simplicity.

  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?

  The tool has zero parameters, so the baseline is 4. The description doesn't need to add parameter semantics.

  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 ('Confirm' and 'report') with a clear resource ('arduino-cli version'). It distinguishes itself from sibling tools by focusing on toolchain availability rather than board operations.

  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 explicitly instructs to call this first before compile/upload, providing clear usage timing. It does not mention alternatives or exclusions, but the context is sufficient for a pre-flight check.

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