Wayland MCP Server

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

With no annotations, the description carries the full behavioral burden. It discloses one meaningful operational constraint — the dependency on a configured VLM provider — which is genuine added value beyond structured fields, but it says nothing about supported image formats, latency/cost, or failure behavior when the provider is unconfigured.

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 short sentences with zero filler, and the core purpose is front-loaded ahead of the prerequisite. Nothing is wasted.

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?

An output schema exists, so return values need not be described, but the definition still falls short: no annotations, 0% parameter documentation, no differentiation from capture_and_analyze or compare_images. For a two-required-param vision tool in a crowded sibling set, the description is under-specified.

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 0% for two required parameters, and the description adds essentially nothing: it never explains that image_path is a filesystem path or that prompt is the VLM instruction. The names are suggestive but not documented, so an agent gets no format or usage detail from either source.

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?

States a specific verb and resource ('Analyze a screenshot') and adds the mechanism ('with a VLM'), which cleanly separates it from capture_screenshot. It does not, however, distinguish itself from siblings like compare_images or capture_and_analyze, leaving the agent to infer which analysis entry point to pick.

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 only guidance is a prerequisite ('Requires a configured VLM provider'); there is no statement of when to use this tool versus compare_images (for two images) or capture_and_analyze (when no image path exists yet). For a tool sitting in a cluster of overlapping image/vision siblings, that omission is costly.

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 are provided, so the description carries the full behavioral burden. It does disclose the two-step capture-then-analyze flow and the VLM provider prerequisite, which is genuine context beyond structured fields, but says nothing about permissions, latency, or failure modes if no provider is configured.

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 short sentences, zero waste, with the action front-loaded and the prerequisite trailing. Appropriately sized for the tool's simplicity.

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?

An output schema exists, so return values need no explanation, and the prerequisite is covered. But the undocumented prompt parameter and the absence of any differentiation from capture_screenshot/analyze_screenshot leave gaps for a tool an agent must choose among nine siblings.

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?

There is one parameter (prompt) at 0% schema description coverage, and the description never mentions it. It fails to explain that the prompt drives the visual analysis question, which is the only semantic the schema lacks.

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 states a specific compound action — capture the screen, then analyze it — which is precise about the verb and resource. However, it does not distinguish itself from the closely related siblings capture_screenshot and analyze_screenshot, leaving the agent to infer that this is the combined variant.

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?

"Requires a configured VLM provider" is a useful prerequisite, but there is no guidance on when to prefer this tool over chaining capture_screenshot with analyze_screenshot. The agent gets a precondition but no selection criteria.

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 are provided, so the description carries the full disclosure burden. It omits the side effect that it writes a PNG to disk (only the schema hints at this), says nothing about output format, permissions, or whether the capture is of the full screen versus a window. The 'measurement rulers' detail is the sole behavioral content.

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?

A single lean sentence with the core action front-loaded and zero filler. It is efficient, though arguably terse given the tool writes a file and has two configurable parameters.

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?

An output schema exists and schema coverage is complete, so return-value explanation is not needed. Still, for a tool with a disk-write side effect and no annotations, and with a near-identical sibling (capture_and_analyze), the description is thin on the details an agent needs to choose and call 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 description coverage is 100%, so both parameters (filename, include_mouse) are already fully documented in the schema. The description adds no parameter-level information beyond the baseline, and notably does not mention the cursor/mouse behavior that include_mouse controls.

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?

States a specific verb and resource ('Capture the screen') plus a distinguishing detail ('with measurement rulers drawn on the result') that separates it from analyze_screenshot and compare_images. However, it never contrasts itself with the closest sibling, capture_and_analyze, so an agent must guess which capture tool is appropriate.

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?

There is no when-to-use, when-not-to-use, or alternative-tool guidance. Given siblings like capture_and_analyze and analyze_screenshot, the description leaves the selection decision entirely to inference.

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 behavioral burden. It usefully specifies the left button and the success/error return shape, but omits important context such as irreversibility/side effects of clicking, required screen state, or modifier-key behavior.

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 action is front-loaded in the first sentence, and the example is compact. The Returns block duplicates the existing output schema, which is mild redundancy but not harmful.

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 zero-parameter tool with an output schema, the description covers the core action and gives an example call. It is largely complete, though it could say more about preconditions (cursor already positioned) and when to prefer this over sibling actions.

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 tool takes zero parameters, so the baseline is 4 and there is nothing for the description to clarify. The empty schema is consistent with the parameterless call shown in the example.

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 states a specific verb and resource: "Simulate left mouse click at current position," which is unambiguous. It does not explicitly name or differentiate itself from siblings like move_mouse or drag_mouse, though the "at current position" phrasing hints at the distinction.

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?

Usage is only implied: "at current position" suggests a prior move_mouse call is needed, but the description never states when to use this versus drag_mouse or execute_action. No prerequisites or exclusions are given.

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 are provided, so the description carries the full behavioral burden. It discloses one useful prerequisite (a configured VLM provider), but says nothing about failure behavior when no provider is set, whether image data leaves the machine, rate/cost implications, or whether the two paths must share format or dimensions.

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 short sentences, front-loaded with the action and followed by the prerequisite. Nothing is padded, though brevity here shades into under-specification rather than efficiency.

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?

An output schema exists, so return values need not be explained. For a two-parameter tool this is borderline adequate, but the type of comparison (semantic diff, similarity score, description comparison) and the input path semantics remain unaddressed.

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 0% for both parameters, so the description must compensate and does not. It never mentions img1_path or img2_path, their expected format, whether they are local paths or URLs, or ordering semantics (does img1 vs img2 matter for the comparison?).

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?

States a specific verb (Compare) and resource (two images) plus the mechanism (VLM), which is enough to distinguish it from the mouse-control siblings. It does not, however, differentiate itself from analysis-oriented siblings like analyze_screenshot or describe_environment, which plausibly also use a VLM.

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 only guidance is a prerequisite ('Requires a configured VLM provider'). There is no statement of when to choose this over analyze_screenshot, capture_and_analyze, or describe_environment, nor any exclusions or preconditions on the images themselves.

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 must carry behavioral disclosure. The verb 'Report' implies a read-only, non-destructive operation, and the description explains what information it surfaces (installed backends, compositor advertising, summary). However, it never explicitly states that it has no side effects, requires no special permissions, or is safe to call repeatedly. The gap is moderate given the read-only nature of the verb.

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, front-loaded with the core purpose. The second sentence efficiently adds the key usage trigger. 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 zero-parameter diagnostic tool with an output schema, the description supplies the essential purpose and usage context. The output schema covers return values, and no parameters require explanation. Nothing critical is missing for an agent to call 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?

The tool takes zero parameters, so there is nothing for the description to add beyond the schema. Baseline for zero parameters is 4; the description appropriately avoids discussing inputs.

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?

States a specific verb ('Report') and resource ('which backends this machine offers, and which were selected'). It is clearly a diagnostic/environment inspection tool, distinct from the action-oriented siblings (move_mouse, click_mouse, etc.) even though it does not name 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?

Gives a clear trigger: 'Call this first when a capture or an input action fails.' This tells the agent when to reach for the tool. It does not provide explicit when-not-to-use conditions or name alternative diagnostic tools, so it falls short of a full 5.

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 does disclose the success/error return shape and gives a concrete call example, but says nothing about which mouse button is used, drag duration/step count, modifier keys, coordinate origin, or whether the call blocks — all relevant behavioral traits for a drag operation.

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?

Front-loaded core sentence followed by compact Args and a single illustrative example; little waste. The Returns block is somewhat redundant since an output schema exists, but it does not bloat the text significantly.

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?

An output schema exists, so the return-value explanation is not strictly needed. Given a 4-parameter, all-required input with 0% schema coverage and no annotations, the description is minimally adequate but omits coordinate semantics and interaction behavior an agent would want.

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 0%, so the description must compensate, and it does label x1,y1 as the start position and x2,y2 as the end position. However, it adds no detail on units, coordinate system origin, screen bounds, or ordering constraints, leaving the semantics thin for an all-required 4-integer API.

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 states a specific verb and resource ('Perform drag operation between coordinates') and the example reinforces it as a mouse drag from (x1,y1) to (x2,y2). This clearly separates it from siblings like move_mouse or click_mouse, though it never names those alternatives 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?

There is no guidance on when to use this over move_mouse or click_mouse, no mention of prerequisites, and no exclusions. The example shows syntax but not selection criteria, so an agent must 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.

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

With no annotations, the description carries the full behavioral burden and does a good job: it documents the return shape ({'success': bool, 'error': str}), discloses chaining semantics, per-action behavior, and even scroll unit semantics (120 = high-def notch, typical 15-120). It omits any statement about side effects, reversibility, or whether actions are destructive, which for an input-simulation tool would be useful, keeping it out of the 5 range.

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?

Front-loaded purpose, then a well-organized action reference and example. It is long but most lines earn their place as a DSL reference. The 'Declared as a dict... strict MCP client rejects' paragraph is a meta-note about a past annotation bug rather than agent-facing invocation guidance, which costs a point.

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 one-parameter tool with an output schema present, the description is nearly complete for invocation: format, actions, units, and examples are all covered. The remaining gap is selection context against the many overlapping siblings, which for a tool of this complexity an agent would benefit from.

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 0% and there is a single 'action' parameter, yet the description fully compensates: it defines the string format for single vs chained actions, enumerates every supported action with its argument syntax, and gives concrete examples. This is meaning that the bare schema does not provide.

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?

States a clear verb+resource ('Execute system actions with chaining support') and even scopes the tool as a general action executor that handles both single and chained sequences. However, it never distinguishes itself from siblings like click_mouse, move_mouse, drag_mouse, and scroll_mouse, which cover the very same underlying actions the DSL exposes. An agent cannot tell from the description why it should route to this general tool versus the specific sibling.

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?

Usage is only implied through examples ('execute_action("click:100,200")') and the format spec. There is no explicit when-to-use guidance, and critically no guidance on when to prefer this tool over the overlapping click_mouse / drag_mouse / scroll_mouse siblings. The reader must infer the choice from the action list.

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 are provided, so the description carries the full behavioral burden. It hints at failure via the error string but says nothing about coordinate bounds/off-screen behavior, negative coordinates, required permissions or desktop-session preconditions, or side effects. Return-shape detail is largely redundant given an output schema already exists.

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?

Purpose is front-loaded in the first line, followed by structured Args/Returns/Examples sections where each line carries information. It is somewhat longer than necessary because the Returns block duplicates the output schema, but nothing is padding.

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 3-parameter tool with zero schema coverage, the description covers every parameter, both call modes, and error signalling, and an output schema covers returns. The remaining gap is behavioral/environmental (bounds, session requirements) and sibling routing, not the mechanics of calling it.

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 0%, so the description must supply all parameter meaning — and it does: x with origin at left, y with origin at top, and relative with its default and its meaning relative to the current position. Two worked examples further disambiguate absolute versus relative calls, fully compensating for the schema gap.

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 opening sentence gives a specific verb+resource ('Move mouse') plus the scope ('to specified screen coordinates'), which is unambiguous and separable from click_mouse/drag_mouse/scroll_mouse. It does not explicitly name or contrast with those siblings, so it stops short of a 5.

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?

There is no guidance on when to use move_mouse versus click_mouse, drag_mouse, or execute_action, nor any prerequisite (e.g. an active desktop session). The examples demonstrate invocation syntax only, not selection criteria, leaving the agent to infer 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 carries the full behavioral burden. It does disclose useful behavioral detail: sign convention (positive=up, negative=down), the unit of measure (one wheel notch), the 120-unit high-definition scale, and typical value ranges. However, it omits prerequisites such as whether the target window must be focused and what side effects or returns to expect.

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 short lines, front-loaded with the core direction semantics before the supporting note on units. The parenthetical about high-definition scroll is slightly tangential but still earns its place by clarifying the unit scale.

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?

An output schema exists, so return values need not be described. For a one-parameter tool with no annotations, the description covers value semantics well but leaves the operational context (focus requirements, what an agent should do before/after scrolling) unspecified.

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 0%, so the description must compensate, and it does: it defines the sign convention, the physical meaning of each unit, and realistic value ranges for the single 'amount' parameter. It never names the parameter 'amount' explicitly, which is a minor gap.

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 a specific verb+resource combination ('Scroll vertically' on the mouse wheel), which is unambiguous against siblings like move_mouse, click_mouse, and drag_mouse. It does not explicitly name or contrast those siblings, so it stops short of a 5.

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?

There is no guidance on when to use scroll_mouse versus the other mouse tools, nor any prerequisites (e.g., window focus, cursor position). The scroll direction semantics are explained, but the when-to-use decision is left entirely to inference.

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