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

Annotations already mark as destructive and open-world. Description adds important context: 'runs an arbitrary command line on the user's machine with their privileges — never pass untrusted input.' Also explains behavior of no_startup_id flag.

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 sentences with no redundancy: purpose, warning, and usage guidance for parameter and siblings. 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?

Covers all needed context given annotations (destructive, open-world), schema (100% coverage, 2 parameters), and existence of output schema. Includes security warning and sibling differentiation.

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. Description adds practical guidance for no_startup_id: 'Set for programs without startup-notification support (avoids a lingering busy cursor).' This adds value 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?

Description clearly states 'Launch an external program via i3's exec' with specific verb and resource, and explicitly distinguishes from sibling tools like focus_window, move_window, set_layout.

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 (launching external programs), when not to use (for built-in i3 verbs), and provides security warning about untrusted input. Explains no_startup_id flag usage.

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 adds value beyond annotations by stating the tool is reversible (consistent with idempotentHint=true and destructiveHint=false) and by explaining the rejection of invalid selector combinations. However, it could briefly mention that only focus is affected, not window position.

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 with no fluff: main purpose and selection options, reversibility, and important constraint/alternative. Front-loaded with key 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 complexity of 8 parameters and multiple selection methods, the description covers core behavior, constraints, and alternatives. Output schema exists, so omission of return value details is acceptable.

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?

Although schema coverage is 100%, the description groups parameters into categories (direction, criteria, parent/child, layer, output) and clarifies mutual exclusivity, which is essential semantics not present in individual schema 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 the verb 'Move keyboard focus' and the resource (i3 window), and distinguishes from sibling `move_window` by specifying that this tool focuses, not moves. It also explains the selection mechanism and the constraint of exactly one selector.

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 explicitly names the alternative `move_window` for moving instead of focusing, and warns that supplying none or several selectors is rejected. This provides clear when-to-use and when-not-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?

Annotations already declare readOnlyHint and destructiveHint. The description adds value by warning about the potentially large config body and explicitly stating 'Read-only'. No contradiction with annotations.

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 sentences, front-loaded with main purpose, then details, then sibling distinction. No wasted words, every sentence adds value.

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 simple tool (one optional param, output schema exists), the description covers returned fields, parameter guidance, and sibling context. 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 coverage is 100% with one parameter described. The description adds practical guidance on when to set include_config_text=false to skip large config body, enhancing the schema's 'can be large' note.

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 inspects i3/Sway configuration state, listing specific fields (version, compositor, config path, config text, binding modes). It explicitly distinguishes itself from siblings by stating it's the only config-introspection tool and directing users to get_tree for live layout.

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 explicit guidance on when to use this tool (config introspection) and when not to include config text (set include_config_text=false to skip large body). It also names the alternative get_tree for live layout, fulfilling both when-to-use and when-not-to-use.

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?

Annotations already declare readOnlyHint=true, destructiveHint=false, and idempotentHint=true. The description adds the cap of 200 windows with a truncated flag and that it returns leaf windows with ids, marks, and location, providing useful behavioral context beyond annotations.

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 concise: five sentences that front-load the main purpose, list filters, provide usage guidance, and mention the cap. No redundant 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 presence of an output schema and rich annotations, the description covers all necessary aspects: return value details (leaf windows with ids, marks, location), usage of id in other tools, and the cap. It is complete for the tool's 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 input schema has 100% description coverage, with each parameter having a clear description. The tool description does not add additional semantic detail beyond listing the filter options, so baseline score of 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 it lists application windows from the i3/Sway layout tree with optional filters. It distinguishes itself from siblings like get_focused, list_workspaces, and list_outputs by naming them explicitly.

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 explicit guidance on when to use this tool (listing windows from the layout tree) and when to use alternatives (get_focused for active window, list_workspaces for workspace summary, list_outputs for monitors). It also explains how to use the returned id with other tools.

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?

Beyond annotations (destructiveHint=true), the description details that the target application is asked to quit, unsaved work may be discarded, no undo, and matching several windows closes all. This adds significant 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?

Two sentences: first states purpose, second provides behavioral warning and alternative. Every sentence earns its place, 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?

For a tool with 5 optional criteria parameters, destructive behavior, and an output schema (not shown but indicated), the description covers purpose, criteria, destructive consequences, and alternative usage. 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 coverage is 100%, so baseline is 3. However, the description adds value by listing the criteria types (class, title, instance, mark, con_id) and implying they are for matching, which reinforces and slightly expands on the schema 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 explicitly states 'Close a window — the focused one, or one matched by class/title/instance/mark/con_id'. It uses a specific verb ('Close') and resource ('window'), and distinguishes from sibling `move_window` by mentioning the destructive nature and alternative.

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 guidance: use to close windows, not to move them out of the way (referencing `move_window`). It also warns about destructiveness and multiple windows matching.

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?

Annotations already declare readOnly, idempotent, not destructive. Description adds detail on returned fields and confirms read-only nature, providing slight additional value.

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, front-loaded with core purpose.

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 zero parameters and good annotations, the description fully covers what the tool does and when to use it. Output schema exists, so return values are documented elsewhere.

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, baseline is 4. Description mentions return fields, no further semantic explanation needed.

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 lists display outputs with specific fields (name, state, workspace, geometry). Distinguishes from sibling tools by mentioning alternatives.

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 advises using before moving windows/workspaces between monitors, and directs to list_workspaces for workspace listing.

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?

Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true. Description adds 'Read-only' which is consistent but doesn't disclose additional behavioral traits beyond the annotations. Minimal added value.

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 concise sentences: first covers the action and output, second provides usage context and sibling differentiation. No redundancy or extraneous text.

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 zero parameters and the presence of an output schema, the description fully covers the tool's purpose, usage, and relationship to siblings. 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?

Tool has zero parameters, and schema describes them (vacuously). Baseline 4 per rubric: '0 params = baseline 4'. Description doesn't need to add param details.

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 'List all active workspaces' and enumerates the specific fields returned. It distinguishes this tool from siblings by contrasting with get_tree and list_outputs.

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 says 'Use this for navigation decisions' and provides concrete alternatives: 'for windows on a workspace use get_tree... for monitors use list_outputs'. This is exemplary 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?

The description discloses that the operation is reversible, adding behavioral context beyond the annotations. Annotations indicate a mutation (readOnlyHint=false) but not destructive, and the description aligns with that.

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 concise (two sentences) yet comprehensive. It front-loads the core actions, then adds details about reversibility and parameter dependencies, followed by sibling tool references. 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 the tool's complexity (multiple actions with parameter dependencies) and the presence of an output schema, the description is complete. It covers all necessary behavioral and usage aspects without 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?

Even with 100% schema description coverage, the description adds significant value by explaining how the action parameter determines which other parameters are required. This is not evident from 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 the tool's purpose: acting on workspaces with specific actions (switch, move_container_to, rename, navigate). It uses specific verbs and resources, and distinguishes from sibling tools like move_window and list_workspaces.

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 explicit guidance on when to use each action and which parameters are required. It also suggests alternatives for other tasks (e.g., move_window for moving a single window, list_workspaces for listing).

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?

Beyond annotations (readOnlyHint=false, destructiveHint=false), the description adds 'Reversible; returns per-command success.' This discloses reversibility and return format, though it doesn't detail side effects or auth requirements.

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 sentences with clear front-loading: purpose first, then constraint, then sibling differentiation. No extraneous 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 tool with 11 parameters, 0 required, 100% schema coverage, and output schema, the description covers destination types, selection options, reversibility, and sibling tools. Missing clarification on criteria combination, but adequate.

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 description coverage is 100%, so baseline is 3. The description adds the constraint 'exactly one destination' but doesn't elaborate on parameter formats or interactions 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 moves a container, specifies selection options (class/title/instance/mark/con_id), and lists possible destinations (direction, workspace, output, scratchpad, screen center). It distinguishes from sibling tools focus_window and manage_workspace.

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 tells when to use this tool vs alternatives: 'To change *focus* rather than move, use focus_window; to move whole workspaces between monitors, use manage_workspace.' Also notes 'exactly one destination' to avoid conflicting parameters.

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?

Annotations already indicate destructiveHint=true and openWorldHint=true. The description adds specific destructive examples (kill, restart, reload, exit) and a validation caveat, providing context beyond the annotations without contradiction.

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 a list of examples, front-loaded with purpose. No unnecessary words; every sentence adds value.

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 an output schema exists (not detailed but present), the description covers purpose, usage, and warnings adequately. Slight gap: no mention of error handling or return format, but not critical for a raw command 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% for the single parameter 'command'. The description adds value by giving concrete examples of acceptable commands (marks, gaps, etc.), going beyond the schema's generic description.

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's purpose: running raw i3/Sway commands as an escape hatch. It lists specific use cases (marks, gaps, bar, scratchpad, reload/restart) and distinguishes from sibling tools by advising to prefer typed tools when available.

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?

Explicit guidance on when to use (operations without dedicated tool) and when not to (prefer typed tools like focus_window). Also includes explicit warning about destructive nature and advising validation.

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?

Annotations already indicate readOnlyHint=false and destructiveHint=false, but the description adds 'Reversible', which is important behavioral context. It also clarifies that 'border_width applies only to the pixel border', providing edge-case behavior beyond the schema.

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 well-structured sentences with all essential information front-loaded. Every sentence adds value 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 full schema coverage and presence of an output schema (as per context signals), the description covers all needed context: what the tool does, usage prerequisites, behavioral notes, and cross-reference to a sibling tool for other functionalities.

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 the description adds semantic value by specifying that at least one of layout/split/border is required (schema allows all null) and that border_width is conditional on border='pixel'. This helps the agent form valid invocations.

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 ('set') and the resource ('focused container layout, split, border'). It distinguishes from the sibling tool 'toggle_window_state' by directing to it for floating/fullscreen/sticky states, ensuring the agent can differentiate.

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 says 'Provide at least one of layout/split/border', giving a clear requirement for parameter selection. Also tells when not to use this tool by referencing 'toggle_window_state' for other window states.

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?

Annotations are all false and provide minimal information, but the description compensates by stating the operation is reversible and explaining the behavior of enable and fullscreen_scope. It does not mention any side effects, but given the tool's nature, this is sufficient.

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 very concise—three sentences with no wasted words. It front-loads the purpose and quickly covers usage details and alternatives.

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 moderate complexity (3 params, all documented in schema, and an output schema exists), the description provides complete guidance on how to use each parameter and when to use an alternative tool. 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 coverage is 100% (baseline 3), and the description adds value by clarifying the enable parameter's toggle vs force behavior and the fullscreen_scope meaning (per-output vs across-all). This goes beyond the schema 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 the tool's action: toggle boolean window states (floating, fullscreen, sticky) on the focused window. It distinguishes itself from sibling tool set_layout, which handles layout/border changes.

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 provides when to use (for boolean window states) and when not to (for layout/border, use set_layout). Also explains the toggle behavior and parameter usage (omit enable to toggle, set true/false to force).

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