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

With no annotations provided, the description carries full burden for behavioral disclosure. It discloses multiple behavioral traits: writes compressed archive + JSON metadata, prunes backups older than retention days (default 7), compress defaults to true, runs pre/post hooks, and that 'full' type errors. This is comprehensive 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.

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

The description is four sentences, each serving a distinct purpose: main action, type support, default behaviors, and hooks. It is front-loaded with the core verb and resource, and every sentence adds essential information without redundancy.

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

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

Given the complexity of 13 parameters and no output schema, the description covers the main operational aspects (what it creates, type-specific requirements, defaults, pruning, hooks). It does not describe the return value or error handling, but this is reasonable for a creation tool where the output is implicit.

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

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

Schema coverage is 100%, so each parameter has a description. The tool description adds value by clarifying parameter relationships (e.g., 'database types require database; files requires paths') and defaults (compress, retention). This contextual information aids parameter selection beyond the schema alone.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

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

The description clearly states it creates a database or file backup over SSH, writing a compressed archive and metadata file. It lists supported types (mysql, postgresql, mongodb, files) and notes that 'full' is not implemented. This specificity distinguishes it from sibling tools like ssh_backup_list and ssh_backup_restore.

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

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

The description provides implicit guidance by stating which types require which parameters (e.g., 'Database types require database; files requires paths'). It also mentions that 'full' is not yet implemented, guiding the agent away from using it. However, it does not explicitly contrast with alternatives like ssh_backup_schedule for scheduled backups.

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

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

Explicitly states 'Read-only: it inspects the filesystem and mutates nothing.', which fully covers behavioral traits. Since no annotations are provided, the description compensates perfectly.

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

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

Two sentences, no wasted words. First sentence covers action and return data, second covers safety and parameters. Highly efficient and front-loaded.

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

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

No output schema, so description appropriately details return data (id, type, size, etc.) and clarifies behavior (read-only, default dir). Covers all necessary info for a listing tool.

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

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

Schema coverage is 100%, but description adds value by clarifying the default for backupDir and explicitly listing the filter options (though schema has enum). This extra context aids correct parameter usage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

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

Clearly states verb 'lists', resource 'backups found in backupDir on remote server', and distinguishes from siblings like ssh_backup_create by focusing on listing existing backups and parsing metadata.

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

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

Explicitly notes read-only nature and optional type filter, but does not provide explicit guidance on when to use vs. alternatives like ssh_backup_create or ssh_backup_restore. Relies on context.

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

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

With no annotations, the description fully discloses destructive behavior: overwriting target, dropping existing objects for PostgreSQL and MongoDB, replacing for MySQL, and supporting files. It also mentions pre/post hooks, providing full behavioral context.

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

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

The description is a single paragraph of 4 sentences, efficient and front-loaded with the core action. Every sentence adds value, though slight reordering could improve scanability.

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

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

Given the multi-engine, destructive nature, the description covers engine behaviors and hooks. No output schema is present, so the return value is not described, but the main operational context is sufficient for a restore tool.

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

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

Schema coverage is 100% and each parameter already has a description. The tool description adds overall context but does not enhance individual parameter meaning significantly. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

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

The description clearly states the tool restores a backup by ID, selects engine based on metadata, and distinguishes from sibling tools like ssh_backup_create and ssh_backup_list. The verb 'restores' and resource 'backup' are specific, and the engines are enumerated.

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

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

The description implies usage when a backup ID is available, but does not explicitly state when to avoid this tool (e.g., for non-destructive operations) or contrast with alternatives like ssh_backup_create or ssh_backup_list. The context is clear but lacks exclusions.

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

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

With no annotations, the description fully discloses that the tool mutates remote filesystem and crontab, needs root, writes a script to a specific path, and deletes backups older than retention (default 7). This is thorough behavioral disclosure.

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

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

The description is two sentences, front-loaded with the main action, and includes critical details without excess. Every sentence earns its place.

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

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

Despite no output schema, the description covers all key aspects: what it does, how it works, side effects, and supported types. It is complete for an agent to understand the tool's purpose and usage.

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

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

All 7 parameters have schema descriptions (100% coverage). The description adds value by explaining the generated script behavior, default retention, and the path location, enhancing understanding beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

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

The description clearly states the tool schedules a recurring backup by writing a script and installing a crontab entry. It specifies supported types (mysql, postgresql, mongodb, files) and retention. This distinguishes it from siblings like ssh_backup_create (one-time backup) and ssh_backup_list.

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

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

The description implies usage for recurring backups and mentions root requirement but does not explicitly guide when to use this vs alternatives like ssh_backup_create or ssh_execute.

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

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

With no annotations, the description fully discloses mutation, default backup behavior, options for owner/permissions/sudo/restart, automatic default detection, hooks, and security restrictions. This provides comprehensive transparency.

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

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

The description is a single paragraph with six sentences, each adding distinct value: main action, state mutation, backup, options, defaults, hooks, restrictions. No unnecessary words.

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

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

The description covers all major aspects: upload method, backup, options, defaults, hooks, security. However, it omits error handling behavior (e.g., what happens if a move fails) and does not describe the return value, leaving minor gaps.

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

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

Schema coverage is 100%, so baseline is 3. The description adds context by explaining the temporary-upload-then-move process and automatic default detection, enriching understanding of parameters like owner and permissions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

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

The description clearly states the tool deploys local files to remote paths using a two-step upload-then-move process. It distinguishes from siblings like ssh_upload by specifying the temporary location and backup behavior.

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

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

The description implies usage via the detailed process but does not explicitly compare to alternatives such as ssh_upload or ssh_backup_create. An explicit 'use this when' statement would improve clarity.

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

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

No annotations provided, so description carries full burden. It discloses overwriting existing local files, read-only remote behavior, local filesystem-only impact, and permission requirements. This fully informs the agent of all behavioral traits.

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

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

Four sentences, each with distinct purpose: main action, safety mode, permission requirement, alternative tool. Front-loaded with key action. No wasted words.

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

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

For a simple file download tool, the description covers all necessary context: single file, SSH user permissions, overwrite behavior, readonly compatibility. No output schema exists but return value is implied. No gaps for typical usage.

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

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

Schema covers 100% of parameters with basic descriptions. Description adds value beyond schema by explaining the overwrite behavior and permission context for 'localPath' and 'remotePath', but schema already conveys the primary meaning.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

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

The description clearly states it downloads a single remote file via SFTP to a local path, and distinguishes from ssh_sync for directories. The verb 'downloads' combined with resource 'one remote file' and destination 'local destination path' is 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.

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

Explicitly states when to use (single file) and when not (use ssh_sync for directories). Also mentions it is allowed on readonly/restricted servers and requires read permission, providing clear guidance on preconditions.

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

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

No annotations provided, so description carries full burden. Discloses alias expansion, OS adaptation, timeout defaults/cap, readonly/restricted restrictions, and output truncation—comprehensive for a command execution tool.

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

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

Concise paragraph with no wasted sentences. Front-loaded with core purpose, each subsequent sentence adds specific behavioral detail.

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

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

No output schema, but description explains return values (stdout, stderr, exit code) and covers edge cases (timeout, truncation, mode restrictions). Complete for a command execution tool.

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

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

Schema coverage is 100% (baseline 3). Description adds value beyond schema by explaining cwd default behavior, timeout range, and command alias expansion, enhancing understanding of each parameter's semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

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

Clearly states it runs a shell command over SSH and returns stdout, stderr, and exit code. Distinguishes from sibling tools like ssh_download or ssh_execute_group.

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

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

Mentions mutability (not read-only) and behavior under readonly/restricted modes, guiding when to use and when not. Could be more explicit about alternatives but provides useful context.

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

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

No annotations exist, so description fully covers behaviors: mutation of remote state, non-idempotent, best-effort, per-server security policy evaluation, timeout (30000 ms), cwd defaults, and strategy-specific delay. No contradictions.

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

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

Description is informative and front-loaded, but slightly verbose. Could condense 'Best-effort: the security policy...' into a more concise statement. However, overall structure is logical and easy to parse.

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

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

Given tool complexity (multiple strategies, non-idempotent, best-effort) and absence of output schema, description covers all essential behavioral aspects. Agent can understand what to expect and how to use parameters.

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

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

Schema has 100% coverage with descriptions. Description adds meaning beyond schema: explains strategy implications, delay role, stopOnError effect, timeout, and cwd default. For example, 'delay' is described as 'between servers in ms (for rolling)' which clarifies its use.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

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

Description clearly states it runs one command on every server in a named group and returns a per-server report, which is specific and distinguishes it from sibling tools like ssh_execute (single server) and ssh_deploy.

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

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

Describes execution strategies (parallel, sequential, rolling), delay, stopOnError, and best-effort behavior. Implicitly indicates use for group-level commands but lacks explicit when-not-to-use or comparison with alternatives.

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

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

The description explicitly states it is read-only, only reads metrics, and changes nothing on the remote host. With no annotations provided, the description fully bears the transparency burden and meets it well.

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

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

The description is three concise sentences, front-loaded with the main purpose, and every sentence adds necessary information. No wasted words.

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

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

Given two parameters, no annotations, and no output schema, the description covers the behavior, safety, parameter details, and result format (parsed JSON with fields). It could mention error handling or SSH prerequisites, but is largely complete for its complexity.

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

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

The schema already describes both parameters (server, detailed). The description adds value by stating the default for detailed (false) and specifying what additional metrics it includes (load average, network). This goes beyond the schema's brief descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

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

The description clearly states it runs a read-only health check via SSH, returning parsed JSON with status, CPU, memory, disk, and uptime. This distinguishes it from siblings like ssh_execute (which runs arbitrary commands) and ssh_service_status (service-specific).

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

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

The description provides parameter guidance (detailed flag) but does not explicitly state when to use this tool vs alternatives like ssh_execute or ssh_process_manager. It implies usage for health checks but lacks explicit when-not-to-use or alternative references.

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

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 that accept and remove mutate local state and are blocked on readonly servers, and warns that autoAccept should be used with caution. This fully informs the agent of behavioral traits.

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

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

Two sentences with no waste. First sentence states the general purpose, second explains all actions and constraints. Information is front-loaded and every sentence earns its place.

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

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

Given the tool has 3 parameters and no output schema, the description is mostly complete. It covers all actions, constraints, and warnings. A minor gap: it doesn't explicitly state that the 'list' action lists all known hosts entries (implied by server not being required), but overall it's sufficient.

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

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

Schema coverage is 100%, so each parameter has a basic description. The tool description adds significant meaning by explaining the purpose of each action value, the mutation safety, and the server requirement per action. It enriches the semantics beyond the schema's enum and boolean descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

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

The description clearly states it manages SSH host key fingerprints in the local known_hosts file, specifying the verb 'Manages' and resource 'SSH host key fingerprints'. It distinguishes five actions (verify, accept, remove, list, check) with explicit behavior, making it distinct from sibling SSH tools.

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

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

The description provides clear context for each action, noting that verify, check, and list are read-only, while accept and remove are mutation actions blocked on readonly servers. It also specifies that server is required except for list, and warns about autoAccept. However, it does not explicitly compare to sibling tools or state when to use alternatives.

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

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

Discloses read-only nature, no connections opened, secrets omitted, and return fields. No annotations provided, so description fully handles transparency.

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

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

Concise, front-loaded with main action, every sentence adds value with no redundancy.

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

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

Fully describes output, side effects, and usage context. No gaps given zero parameters and no output schema.

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

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

No parameters exist; description explicitly states 'takes no parameters' and explains purpose without needing schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

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

Explicitly states it lists SSH servers from configuration, with specific fields returned. Distinguishes from siblings by being a read-only discovery tool.

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

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

Advises using it as a first call to discover server names accepted by other tools, providing clear when-to-use guidance.

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

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

With no annotations provided, the description fully discloses behavioral traits: which actions are read-only vs. mutating, that kill may be blocked depending on server config, and default values for signal, sortBy, and limit. This is comprehensive and leaves no ambiguity.

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

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

The description is three sentences, efficiently structured with the main purpose first, then action details, then defaults and filters. No extraneous information; every sentence earns its place.

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

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

Given the tool's complexity (three actions, seven parameters, no output schema), the description covers all relevant aspects: actions, parameter dependencies, defaults, and behavioral constraints. The lack of output schema is acceptable as it is not provided, and the description does not need to explain return values.

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

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

Input schema has 100% coverage, so baseline is 3. The description adds value beyond the schema by clarifying that pid is required for kill and info, that filter narrows by name/command, and that defaults apply to signal, sortBy, and limit. It also explains the action parameter's semantic groups, which is not fully captured in schema descriptions alone.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

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

The description clearly states the tool lists, inspects, or terminates processes on a remote server over SSH. It explicitly names the three actions (list, info, kill) and distinguishes itself from siblings focused on file operations, tunnels, or backups.

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

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

The description provides guidance on when to use each action: list for read-only top processes, info for details (read-only), kill for termination (mutation). It also notes that kill is blocked on readonly servers, implying when not to use it. However, it does not explicitly contrast with sibling tools or give alternative tool recommendations.

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

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

No annotations provided, so the description bears the burden. It clearly states the tool is read-only and only inspects status. It could mention SSH requirements or that it queries systemctl, but the current disclosure is adequate for safe usage.

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

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

Two sentences, no redundancy. The first sentence states purpose and output, the second adds safety and parameter detail. Every sentence is necessary and well-structured.

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

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

For a two-parameter tool without output schema, the description adequately describes the return structure (JSON per service, counts, health rating) and the automatic name resolution. No gaps given the simplicity and no annotations.

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

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

Schema coverage is 100% with descriptions for both parameters. The description adds value by explaining that the services parameter lists service names, provides examples, and mentions automatic resolution to unit names. No additional info for server parameter, but overall helpful.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

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

The description clearly states the verb 'checks', the resource 'running state of system services on a remote server', and the output format (JSON per service, counts, health rating). It distinguishes from sibling tools like ssh_process_manager which manages processes.

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

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

Explicitly states the tool is read-only and does not start/stop/restart services, guiding the agent to use it for inspection only. No explicit alternatives or when-not-to-use, but the read-only hint is strong usage guidance.

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

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

With no annotations, the description fully covers behavioral traits: it affects only local state, closing is irreversible, and for the server option it reports count of closed tunnels. No contradictions.

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

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

Three well-structured sentences: first states action and scope, second explains options, third warns about finality. Every sentence is necessary and informative—no redundancy.

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

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

Given the tool's complexity (two optional but mutually exclusive parameters, no output schema), the description completely covers behavior, parameter constraints, and side effects. No gaps remain.

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

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

Schema already has descriptions for both parameters (100% coverage), but the description adds essential context: the mutual exclusivity rule, that server closes all tunnels, and that the operation reports the number closed—significantly beyond schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

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

The description uses 'tears down' as a specific verb for the 'ssh tunnels' resource, clearly distinguishing it from sibling tools like ssh_tunnel_create (creates) and ssh_tunnel_list (lists). It also clarifies scope ('affects only local tunnel state').

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

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

Explicitly states that exactly one of tunnelId or server must be supplied, explains what each does, and warns that supplying neither raises an error. The finality ('cannot be undone') provides crucial guidance.

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

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

With no annotations, the description carries the full burden. It discloses that the tunnel keeps running until closed, returns a tunnel ID, and defaults localHost to 127.0.0.1. It does not mention authentication or background execution, but overall is transparent.

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

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

Two sentences: first explains purpose and behavior, second details parameter semantics. No waste, every sentence adds critical information.

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

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

Given the tool's complexity (3 tunnel types, parameter dependencies), the description covers the key behaviors and return value. No output schema exists, but the return value (tunnel ID) is mentioned. Minor gaps like blocking vs async are not critical.

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

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

Schema coverage is 100%, so baseline is 3. The description adds significant value by explaining when remoteHost/remotePort are required (local/remote) vs ignored (dynamic), and that localPort defaults to 127.0.0.1. This exceeds the schema's bare descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

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

The description clearly states it opens an SSH tunnel for port-forwarding or SOCKS proxy, with a specific verb ('opens') and resource ('SSH connection'). It distinguishes from sibling tools like ssh_tunnel_close and ssh_execute by focusing on tunnel creation and return of a tunnel ID.

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

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

The description explains when to use each type (local/remote/dynamic) and which parameters are required or ignored. It does not explicitly state when not to use this tool, but the context is clear enough for an agent to decide.

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

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

No annotations provided, but the description explicitly states 'Read-only: it does not create, modify, or close anything', providing clear behavioral transparency beyond the tool's function.

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

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

Two sentences, each serves a clear purpose: first states the function and list of fields, second clarifies read-only nature and parameter usage. No unnecessary words.

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

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

No output schema, but description lists the fields returned. Given the tool's simplicity and the sibling tools context, it provides enough information 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.

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

Schema coverage is 100% (one parameter with description). The description adds value by explaining the effect of omitting the parameter ('list every active tunnel') and that it filters to one server.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

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

The description uses specific verbs ('lists') and clearly states the resource ('active SSH tunnels'), listing many fields. It distinguishes from siblings like ssh_tunnel_create and ssh_tunnel_close by stating it is read-only.

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

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

It explains when to use (to list active tunnels) and what it does not do (create/modify/close). The optional server parameter usage is explained. Could explicitly mention alternatives, but context is clear with sibling names.

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

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

With no annotations provided, the description fully discloses behavioral traits: overwriting existing files, non-idempotent nature, no backup creation, no sudo, and server security mode restrictions. No contradictions.

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

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

Concise paragraph with no redundant sentences. Key information is front-loaded: action, target, and overwriting behavior. Every sentence adds necessary detail.

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

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

Given three required parameters and no output schema, the description covers all essential aspects: operation, side effects, prerequisites, constraints, security, and alternative. No gaps.

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

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

Schema covers 100% of parameters with basic descriptions. The tool description adds valuable context like 'over SFTP', 'overwriting', and 'requires local file to exist', enhancing the meaning beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

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

The description clearly states 'Uploads one local file to a remote destination path over SFTP' with a specific verb and resource. It distinguishes from sibling tools by mentioning 'For directory trees use ssh_sync instead'.

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

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

Explicitly states when to use (single file upload), prerequisites (local file must exist, remote path writable), blocking conditions (readonly/restricted servers), and an alternative (ssh_sync for directories).

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