Server Quality Checklist

Tool Scores

• ubuntu_nginx_controlC
  2.4/5.0
  Behavior1/5

  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 disclosing behavioral traits. It only states 'Control Nginx web server on Ubuntu' without mentioning that actions like start, stop, or reload mutate system state, that sudo is likely involved, or what the output/return value looks like. This is inadequate for a service-control tool.

  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 short sentence with no wasted words, and the key resource ('Nginx') is front-loaded. However, it is so sparse that it sacrifices informative value, though that is not purely a conciseness issue. It could benefit from listing the actions, but as written it is structurally efficient.

  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 output schema and no annotations, the description does not explain the operational context: it doesn't mention that it uses an SSH connection, that some actions are destructive, or how results are returned. Given the sibling tools, an agent might infer the domain, but the description alone is insufficient for confident 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%: each parameter is described, including the allowed actions for the 'action' parameter. The tool description adds no extra semantic meaning beyond what the schema already 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.

  Purpose3/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description uses the vague verb 'Control' but identifies a specific resource: 'Nginx web server on Ubuntu'. It doesn't enumerate the specific operations (start, stop, reload, etc.), making the purpose broad. It is distinguishable from sibling tools like ssh_exec because it targets Nginx specifically, but the verb lacks precision.

  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?

  The description provides no guidance on when to use this tool versus alternatives such as ssh_exec or other ubuntu_* tools. There is no mention of prerequisites (e.g., Nginx installed, active SSH connection) or scenarios where this tool is preferred. Usage is only implied by the tool's name and the presence of sibling tools.

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

• ubuntu_website_deploymentC
  2.4/5.0
  Behavior1/5

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

  There are no annotations, so the description carries full responsibility for disclosing behavioral traits. It fails to mention that the tool may overwrite remote files, run with sudo, require an active connection, or that 'restore' modifies existing site state. It also does not explain the backup behavior or implications of the 'createBackup' default. This is a significant transparency gap for a tool with mutating actions.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness3/5

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

  The description is a single sentence with no fluff, but it is under-specified for a tool with 7 parameters and 3 distinct actions. It is concise in the sense of being short, but it omits required function details, so it is not appropriately sized for the tool's complexity.

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

  Completeness1/5

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

  Given the tool's complexity (7 parameters, 3 actions, no output schema, no annotations), the description is severely incomplete. It only mentions deploy and backup, omits restore, connection requirements, default paths, and behavior. An agent would have to rely on parameter descriptions alone to understand how to use this tool effectively.

  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 description. The tool description adds minimal extra meaning by mentioning 'deploy' and 'backups', which loosely maps to the action and createBackup parameters, but it does not clarify the meaning of 'restore' or the roles of path parameters. Baseline 3 is appropriate because the schema already 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 states a clear verb and resource: 'Deploy website files and create backups on Ubuntu'. This differentiates it from generic SSH file tools, though it omits the 'restore' action available in the schema. The name and description together make the tool's primary purpose evident.

  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 given for when to use this tool vs. alternatives like ssh_upload_file, ssh_exec, or other ubuntu_* tools. There are no prerequisites mentioned (e.g., active SSH connection) or exclusions, leaving the agent to infer usage from the name alone.

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

• ubuntu_ssl_certificateC
  2.6/5.0
  Behavior1/5

  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 doesn't mention that this tool modifies the server's certificate store, requires root/sudo, or makes network requests to Let's Encrypt. The vague verb 'Manage' gives no safety or side-effect information.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness3/5

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

  The description is one short sentence, making it concise and front-loaded. However, it is so generic that it borders on under-specification, repeating the tool's name without meaningful value. It earns a middle score for brevity but lacks substance.

  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 output schema and no annotations, the description is the only narrative source for expected behavior. It doesn't explain return values, error conditions, or effects on the system. The schema helps with parameters, but the description is insufficient for a tool that can issue and renew certificates.

  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 documents all six parameters with descriptions (100% coverage), so parameter semantics are already provided programmatically. The description adds no additional meaning beyond what the schema contains.

  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 identifies the resource (Let's Encrypt SSL certificates on Ubuntu) and implies management operations, but the verb 'Manage' is broad and doesn't specify concrete actions like issue, renew, status, or list. It is clear enough to distinguish from sibling tools (which handle SSH, nginx, firewall), but lacks precision for a high score.

  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?

  The description provides no guidance on when to use this tool instead of alternatives like ubuntu_nginx_control or ssh_exec. It doesn't mention prerequisites (e.g., domain DNS pointing to server, HTTP server running for webroot validation) or exclude any cases.

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

• ubuntu_ufw_firewallC
  2.9/5.0
  Behavior2/5

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

  With no annotations to rely on, the description fails to disclose important behavioral traits: actions are mutating and high-risk (e.g., deny could lock out the SSH session), sudo may be required (though a sudo parameter exists), and firewall state changes persist. The word 'manage' does not convey the potential for disruption.

  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 with no filler. It efficiently communicates the tool's general purpose, though it is minimal. It earns its place without being verbose, but could be slightly more informative without sacrificing concision.

  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?

  Given the tool's complexity (multiple actions, unclear safety implications, no output schema, no annotations), the description is far from complete. It lacks guidance on rule syntax, what 'delete' or 'reset' entails, and any warnings. The schema covers parameters but not operational context.

  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 description adds no parameter meaning, but the schema provides comprehensive descriptions for all 6 properties (100% coverage). The action field enumerates possible values, and port/protocol descriptions are clear, so the description's lack of parameter detail is not a major gap.

  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 the resource (Ubuntu UFW) and a managing action. It distinguishes from siblings like ssh_exec or nginx_control, though 'manage' is somewhat broad. The schema's action parameter grounds the specific operations, making the purpose unambiguous.

  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 like ssh_exec, nor does it note prerequisites such as an active SSH connection (connectionId required). It neither mentions when to use it nor when not to, leaving the agent without decision context.

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

• ubuntu_update_packagesC
  2.9/5.0
  Behavior2/5

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

  With no annotations, the description carries the full burden of behavioral disclosure. It states 'update system packages' but does not explain that this likely runs apt-get update/upgrade, may require sudo, or could modify the system and reboot services. Side effects are 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 with no wasted words. However, it is extremely brief and omits useful context that could be included without bloating the text.

  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?

  Given the tool has 5 parameters, no output schema, and no annotations, the description is under-specified. It does not explain what 'update' entails, the role of connectionId, or what the tool returns (e.g., command output). The schema provides parameter details, but overall context is lacking.

  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 descriptions for 100% of the 5 parameters, including sudo, upgrade, autoremove, connectionId, and securityOnly. The description adds no additional parameter semantics beyond what the schema already conveys, so the baseline of 3 applies.

  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 a clear action ('Update') and resource ('system packages') with a platform qualifier ('on Ubuntu'). It distinguishes itself from sibling tools like nginx_control or ssh_exec, though it relies on the name for full distinction.

  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 alternatives such as ssh_exec for running apt commands manually. There is no mention of prerequisites, context, or exclusions.

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

• ssh_disconnectB
  3.3/5.0
  Behavior2/5

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

  No annotations are provided, so the description must fully disclose behavior. It states the action but does not mention consequences like terminating active sessions, idempotency, or permission requirements, which is a gap for a state-changing operation.

  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 unnecessary words. It is perfectly sized for a simple 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?

  For a tool with one parameter and no output schema, the description is largely sufficient. However, the lack of annotations and behavioral context about what happens when disconnecting (e.g., killing active processes) leaves minor ambiguity, making it adequate but not exemplary.

  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 documents the single parameter connectionId with a clear description, and schema description coverage is 100%. The tool description adds no additional meaning beyond what the schema already 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 uses a specific verb 'Close' and resource 'SSH connection', making the action unambiguous. It clearly distinguishes from sibling tools like ssh_connect and ssh_list_connections.

  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?

  The description does not provide any guidance on when to use this tool, such as after completing operations or when needing to terminate a connection. It offers no exclusions or alternatives.

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

• ssh_upload_fileB
  3.3/5.0
  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. It does not state whether the upload overwrites existing files, requires an active connection, or has any side effects on the remote server. The description is too terse to convey these important behaviors.

  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 wasted words. It is appropriately front-loaded, stating the core action immediately, and is easily parsed by an agent.

  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?

  For a simple file upload tool with fully described parameters, the description is minimally viable. However, it lacks behavioral context such as overwrite policy, required connection state, and any error conditions, which could affect an agent's invocation. The absence of an output schema means description should clarify return values, but it does not.

  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% coverage with clear descriptions for all three parameters (localPath, remotePath, connectionId). The description adds no additional parameter semantics beyond what the schema already states, 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 ('Upload'), the object ('a file'), and the destination ('remote server'), which is specific and distinguishes this tool from siblings like ssh_download_file and ssh_read_file. The verb-resource pairing is unambiguous and matches the tool's 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?

  The description provides no guidance on when to use this tool versus alternatives such as ssh_download_file or ssh_exec. It also does not mention prerequisites like having an active SSH connection, though the schema hints at this via connectionId.

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

• ssh_download_fileB
  3.4/5.0
  Behavior2/5

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

  With no annotations, the description carries the full burden. It only states the basic operation and provides no details about overwrite behavior, permission requirements, binary safety, or connection prerequisites. Significant behavioral gaps remain.

  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 wasted words. It is front-loaded with the core action and resource.

  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?

  This is a simple tool but lacks behavioral details such as overwrite handling, connection requirement, and success/failure indicators. No output schema or annotations exist, so the description should provide more context to be 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 description coverage is 100%, so each parameter is documented. The description adds no extra parameter context beyond the schema, which serves as the baseline 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 clearly states a specific action (download) with source (remote server) and destination (local path). It distinguishes itself from siblings like ssh_upload_file (opposite direction) and ssh_read_file (reading vs transferring).

  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 copying files from remote to local, but it does not explicitly state when to prefer this over ssh_read_file or other alternatives. Context is clear but no exclusions or alternative references are provided.

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

• ssh_list_filesB
  3.4/5.0
  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 behavioral disclosure burden. It only states the action without revealing details like whether it lists recursively, includes file metadata, or how errors are handled. For a read operation, 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, tightly-worded sentence. It is concise, front-loaded, and free of unnecessary words.

  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 should disclose what the tool returns (e.g., list of filenames, full paths, metadata) and any limitations. It does not. For a simple tool it is usable, but it leaves meaningful gaps.

  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% description coverage, so baseline is 3. The description does not add meaning beyond the schema—both remotePath and connectionId are adequately defined in the schema already.

  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 files in a directory on the remote server' with a specific verb and resource. It distinguishes itself from siblings like ssh_read_file and ssh_download_file by focusing on listing directory contents.

  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 you need to list remote directory contents) but does not explicitly mention alternatives or exclusions. Since there are sibling tools, more explicit guidance would be better, but the basic context is present.

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

• ssh_connectA
  3.7/5.0
  Behavior2/5

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

  No annotations are provided, so the description is the sole source of behavioral info. It describes authentication options but omits side effects (creating a persistent connection), failure conditions (unreachable host, bad credentials), or return value (connectionId). This significant gap is not covered elsewhere.

  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 two-sentence description is tight: first sentence states purpose, second covers principal usage patterns. No redundant text.

  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 8-parameter schema and no output schema, the description only partially captures the tool's behavior. It doesn't explain the return value (connectionId defaulting), when the connection is established (e.g., persistent session), or how to use it with sibling tools. The rich schema descriptions compensate for parameter semantics, but behavioral completeness is lacking.

  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 has 100% coverage, so the baseline is 3. The description adds a key clarification: you can pass either a profile or a Host alias, or provide host/username/key directly, which helps disambiguate which parameters to use together. This adds value beyond 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 connects to a remote server via SSH and specifies the supported ways to specify the target (profile, host alias, or direct host/username/key). This distinguishes it from sibling tools like ssh_exec, ssh_list_connections, and file transfer tools.

  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 how to provide connection information (via profile, host alias, or direct host/username/key) but does not explicitly discuss when to use this tool versus alternatives such as ssh_exec (which requires an existing connection) or ssh_list_connections. The usage is implied by the tool name and sibling context but not stated.

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

• ssh_read_fileA
  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 discloses the read-only nature implicitly and the active connection requirement, but it doesn't mention potential truncation due to maxBytes, permission errors, or what happens if the file is missing. This is a minimal but not comprehensive 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?

  The description is extremely concise: two sentences that front-load the purpose and immediately provide usage context. Every word earns its place with 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 3-parameter read tool with no output schema, the description covers purpose, usage, and a prerequisite. It omits return-format details and error behavior, but given the tool's simplicity and full schema coverage, it is sufficiently complete for an agent 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?

  Schema description coverage is 100%, so the baseline is 3. The description adds no additional parameter-level detail beyond what the schema already provides, so no extra credit is warranted.

  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: 'Read and return the contents of a file on a remote server.' It uses a specific verb and resource, and differentiates from siblings by explicitly mentioning use cases like 'explain, analyze, review, or show a file' versus downloading.

  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 explicit guidance with 'Use this when the user asks to explain, analyze, review, or show a file from a server' and notes a prerequisite ('Requires an active SSH connection'). However, it doesn't explicitly mention alternatives or when not to use it, which 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.

• ssh_list_connectionsA
  4.2/5.0
  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 reveal that the tool reads from ~/.ssh/config and lists both active connections and Host entries, which is useful context. However, it does not explicitly state whether the operation is read-only, how 'active' is determined, or what happens if the config file is missing. This is adequate but not rich.

  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-loaded with the primary action, and provides a practical usage example. Every word earns its place; there is no fluff or repetition.

  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 simplicity (no parameters, no annotations, no output schema), the description is fairly complete. It explains what the tool lists, the source, and when to invoke it. The mention of 'find the right connectionId' hints at the output's purpose. It could additionally describe the output format, but for this simple tool, the coverage is strong.

  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 for this dimension is 4 per the rubric. The description adds no parameter explanation because none is needed. It does provide context about what the output is used for (finding the right connectionId), which indirectly clarifies the purpose of any returned data.

  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 active SSH connections and Host entries from ~/.ssh/config'. It uses a specific verb ('List'), identifies the resource (SSH connections and Host entries), and provides the source file. This distinguishes it from sibling tools like ssh_connect or ssh_exec, which perform actions rather than listing.

  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 tells when to use the tool: 'Call this when the user mentions a server by name (e.g. "beta server") to find the right connectionId.' This is clear contextual guidance, though it does not mention when not to use it or name alternatives. Since the task is simple and the trigger condition is well-defined, this is sufficient.

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

• ssh_execA
  4.3/5.0
  Behavior4/5

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

  Since no annotations are provided, the description carries the full burden of behavioral disclosure. It discloses that destructive commands are blocked with examples, which is key safety behavior. However, it does not specify what happens when a blocked command is attempted (e.g., error returned) or whether the command output is returned. This is a minor gap given the absence of annotations.

  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, two sentences long, and front-loaded with the primary purpose. Every sentence earns its place: the first defines the scope, the second lists blocked commands and provides an alternative for file reads. No redundancy or fluff.

  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 ideally explain what is returned (e.g., stdout/stderr, exit code). It does not. While it covers safety and usage, it omits return-value behavior, which is a notable gap for a command execution tool. The completeness is adequate but not thorough.

  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 each parameter having a description in the input schema. The description adds no new parameter-specific semantics beyond what the schema already provides. The mention of 'Use ssh_read_file to read files instead of cat' relates to command usage but not to parameter details, so the score remains at the baseline 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 clearly states the tool's function: 'Execute a read-only or safe command on the remote server.' It distinguishes itself from siblings by explicitly mentioning ssh_read_file for reading files and provides a concrete list of blocked commands, making the purpose specific and unambiguous.

  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 gives explicit usage context: it is for safe commands, destructive commands are blocked, and it names an alternative tool (ssh_read_file) with the directive 'Use ssh_read_file to read files instead of cat.' This clearly tells the agent when to use this tool versus a sibling.

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