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

With no annotations, the description must carry the full behavioral burden. It discloses that the path is local and that GeoPackage sublayer syntax is supported, but says nothing about mutation side effects, required permissions, error handling, or what happens when the layer 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?

A single, front-loaded sentence with no wasted words; it immediately states the action and the key path syntax 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?

For a mutation tool with no annotations, no output schema, and 0% schema coverage on three parameters, the description is too thin. It should explain 'kind' and 'name' semantics, prerequisites, and side effects to be complete enough for reliable invocation.

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 explain all three parameters. It clarifies the 'path' parameter (local path and GeoPackage sublayer syntax) but provides no meaning for 'kind' or 'name', leaving two parameters undocumented.

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 ('Add') and resource ('layer') and clarifies support for vector/raster from a local path. It is clear about what the tool does but does not explicitly distinguish it from siblings like remove_layer or list_layers.

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 offers no guidance on when to use this tool versus alternatives, nor any preconditions (e.g., project must be open, path must be local). It implies usage from the phrase 'from a local path' but leaves selection criteria unstated.

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 discloses that the click is deferred and that the reply is immediate so a modal dialog does not block, which is important context. However, it does not describe failure behavior, required window context, or what the immediate reply contains, leaving significant behavioral gaps for an interaction 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 two compact sentences and front-loads the core action and the key sibling exclusion. Every sentence adds useful information without repetition.

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 four-parameter interaction tool with no annotations, no output schema, and zero schema description coverage, the description is not complete enough. It omits the required `window` parameter, the meaning of `index`, and error/return behavior, even though it does explain deferred clicking.

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, but it only clarifies two of the four parameters: `object_name` and `text`. It does not explain the required `window` parameter or the optional `index` parameter, leaving half of the parameters undocumented.

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: clicking a button/checkbox/tool button by object name or visible text. It also explicitly distinguishes this tool from the sibling `trigger_action` for QActions and menu items, so an agent can select the correct tool without inspecting schemas.

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 provides explicit when-to-use and when-not-to-use guidance by naming `trigger_action` as the alternative for QActions/menu items. The target elements and lookup methods are also clearly scoped.

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 the description carries the full behavioral burden, and it discloses almost nothing: "(deferred)" hints the close is not synchronous but never explains what deferred means in practice. Nothing about what happens to unsaved state, what occurs with an invalid or already-closed window, or whether the call is idempotent.

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?

It is short and front-loaded, which is good, but at this length the brevity reads as under-specification rather than economy. The one decorative element, "(deferred)", adds ambiguity instead of 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?

A one-parameter tool with no annotations, no output schema, and 0% schema coverage needs the description to establish the identifier format and the deferred-close semantics. Neither is present, so an agent cannot invoke this tool with confidence.

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 the single required parameter "window" is a bare string with no format documented anywhere. The description never says whether it expects an ID, a title, a handle, or a name, so it fails to compensate 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 verb+resource pair "Close a window" is identifiable, but the parenthetical "(deferred)" is cryptic and undercuts precision — an agent cannot tell whether the close is immediate, queued, or only scheduled. No differentiation from the obvious sibling list_windows or from any other window-related 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?

There is no statement of when to use this tool, when not to, or which alternative applies. With siblings like list_windows in the catalog, the description gives no routing signal at all, leaving the agent to infer everything from the name.

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 behavioral burden. It usefully discloses that hidden widgets are skipped by default, that only_named reduces noise, and how child vs. window geometry coordinates differ, but it does not state the output format, read-only/safety profile, or behavior of max_items/include_internal.

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 short sentences, front-loaded with the core operation. Each sentence adds useful information without repetition or filler.

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 five-parameter tool with no annotations and no output schema, the description provides solid purpose and some behavioral guidance. It is not complete because it omits the output shape, max_items/include_internal semantics, and any routing to sibling tools.

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 for five undocumented parameters. It explains the window selector, visible_only default behavior, and only_named, but leaves max_items and include_internal unexplained.

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: 'Dump the widget tree of a window.' It also names the selector form (objectName or title), making it readily distinguishable from sibling operations such as set_widget, click_widget, and list_windows.

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 implied by the purpose ('dump the widget tree of a window') and by guidance on hidden widgets and only_named. However, it does not explicitly say when to use this tool versus alternatives such as list_windows, inspect_layer, or set_widget.

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 discloses arbitrary Python execution, available QGIS objects, the result variable, and the exec opt-in requirement, but omits side-effect, failure, and return-channel details important for code execution.

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 compact sentence front-loads the action and packs scope, result handling, and the opt-in prerequisite without 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?

The description covers the essential invocation context and result assignment, but for a dangerous arbitrary-code tool with no annotations and no output schema, it lacks detail on return behavior, errors, and side effects.

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: it clarifies that code is Python executed inside QGIS with iface and project in scope and that the code should assign result. That adds substantial meaning beyond the bare string parameter.

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: execute arbitrary Python inside QGIS, with explicit execution scope (iface, project). It is clearly distinct from algorithm/recipe tools, though it does not name those siblings 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?

Mentions a prerequisite (exec opt-in), which implies this tool is for environments where that permission is enabled. However, it does not state when to prefer this over safer siblings such as run_recipe or run_algorithm.

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 does indicate the conceptual return content (parameter and output definitions), but never states that this is a read-only lookup, what happens with an unknown or malformed algorithm_id, or any formatting/error behavior. For a tool with zero annotation coverage, this is a significant gap.

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 short sentence that front-loads the resource and includes an example inline. It is efficient, though bordering on under-specified rather than genuinely concise.

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 one-parameter read tool with no output schema, the description covers what is returned at a high level. Still missing are the ID format rule (only hinted by example) and any indication of what the returned parameter definitions look like, which an agent needs before invoking run_algorithm.

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?

With one parameter and 0% schema description coverage, the description must compensate. The example 'native:buffer' is genuinely useful because it reveals the required provider:name ID format, which the schema does not convey. However, it does not explain required vs optional algorithm parameters or any other ID syntax constraints.

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 names a specific resource and scope: the parameter and output definitions of a Processing algorithm, with a concrete example ID ('native:buffer'). An agent can distinguish it from list_algorithms (enumerates algorithms) and run_algorithm (executes one). The retrieval verb is only implied by the tool name rather than stated, so it falls 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 explicit guidance on when to call this versus siblings such as list_algorithms or run_algorithm. The natural workflow (inspect params before running an algorithm) is left entirely to inference. No prerequisites, no exclusions, no mention of 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?

With no annotations, the description carries the full behavioral burden. It lists what information is surfaced but never states that the operation is read-only/safe, whether it has side effects, what the return structure looks like, or whether it may be slow. The listing of fields is useful context but falls well short of full 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?

A single compact sentence listing the returned items, with the most important version/platform information front-loaded. It is telegraphic but wastes no 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, no-output-schema info tool, enumerating the returned data categories is the key missing piece and is largely covered. However, the description omits the return format/structure and any behavioral notes, leaving a modest gap for an agent deciding whether to rely on this tool for diagnostics.

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. There is nothing further for the description to explain about 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?

The description enumerates the data returned (QGIS/Python/Qt versions, platform, profile dir, project, probe home and output dirs), which implies an environment/diagnostic info retrieval tool. However, it is a noun-phrase fragment with no verb/resource framing and does not distinguish it from sibling diagnostic tools like ping. Purpose is inferable but not stated crisply.

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?

No guidance on when to call this versus alternatives such as ping, read_log, or list_layers. The diagnostic nature is implied by the listed fields, but there are no explicit use-case cues or 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?

No annotations are supplied, so the description carries the full burden; it does disclose the returned content categories (vector fields/geometry, raster bands/nodata, sample features), which is real behavioral value. It omits whether the call has side effects, permission requirements, and how it fails for an unknown layer.

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 dense sentence with the resource and the return categories front-loaded; nothing is wasted. It is perhaps too compressed, but it is structurally sound and easy to scan.

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?

With only two parameters and no output schema, the description should explain what the call returns and any failure behavior. It names the content categories but not the response shape, and says nothing about invalid layer identifiers or the meaning of the sample default.

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% and both parameters are bare, so the description must compensate. It usefully clarifies that 'layer' accepts an id or unique name, and hints that 'sample' relates to sampling features, but does not state that sample is a count or how sample=0 behaves.

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 (inspect/details) and resource (layer), plus the content returned for each layer type (fields/geometry vs bands/nodata). It distinguishes itself from siblings like list_layers by being about a single layer's internals, though it never says so 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?

Usage is only implied: an agent can infer this is for examining one known layer, complementing list_layers for discovery. There is no explicit when-to-use, when-not-to-use, or named alternative, and no prerequisite about obtaining a valid layer id/name first.

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 supplied, so the description carries the full burden. Calling it 'List' implies a read-only operation and the trigger_action pairing hints at a two-step discovery flow, but it says nothing about what happens if the target window doesn't exist, whether hidden/disabled actions are returned by default, or what the results look like. Adequate, but thin for a tool with zero annotation coverage.

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 tight sentences that front-load the resource definition and end with the actionable follow-up. No filler, no repetition of the schema.

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, zero-required-parameter read tool with no output schema, the description covers purpose and the trigger_action pairing, which is most of what matters. Missing is the window-argument contract and any sense of return shape (e.g., names vs. objects), so an agent still has to guess how to go from results to a trigger_action call.

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% across 3 parameters, and the description only compensates for one of them: `text` is clarified as a substring filter. `window` is never explained (the default 'QgisApp' and how window names relate to list_windows is left implicit), and `include_hidden` — the parameter with the most behavioral consequence — is not mentioned at all.

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 (List) and a precisely defined resource (QActions), and the parenthetical explains what a QAction is in practical terms — menu items and toolbar buttons where plugins register entry points. That definition alone separates it from siblings like list_windows, list_plugins, and list_algorithms.

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 an explicit workflow: list here, then call trigger_action to launch the plugin, which is the key pairing an agent needs. It also says to use `text` for substring filtering, though it doesn't say when NOT to use this tool (e.g., when list_windows/inspect_layer would answer the question instead).

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 disclosure burden but says nothing about pagination limits (the schema's `limit` defaults to 50, implying truncation risk), result ordering, or the shape of returned algorithm entries. Nothing indicates whether the tool is a pure read (safe to call freely) or has side effects, which matters for an agent deciding whether to probe it.

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?

One short, front-loaded sentence with no filler, which is structurally sound. However, at this length against a three-parameter tool it reads as under-specification rather than deliberate economy.

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 schema coverage, no annotations and no output schema, the description should explain the provider filter, the limit default's truncation effect, and roughly what a returned algorithm record contains. It covers only the search key, leaving an agent under-informed on how to call the tool correctly at scale.

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, yet it only addresses `search` (substring matching against id/name). `provider` and `limit` are never explained in prose, leaving two of three parameters relying on bare titles and defaults.

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 gives a specific verb ('Search') and resource ('Processing algorithms') plus the matching key (id/name substring), which is enough to distinguish it from run_algorithm, get_algorithm_params and list_plugins. It stops short of 5 because it describes only the substring-search mode and never says that omitting `search` enumerates all algorithms, so the relationship between the tool's name (list_algorithms) and its stated behavior is left slightly ambiguous.

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 versus siblings such as get_algorithm_params (to inspect a chosen algorithm) or run_algorithm (to execute one), and no statement of preconditions or when-not-to-use. The agent must infer the discovery-then-inspect workflow from tool names 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?

No annotations are provided, so the description carries the full behavioral burden. It discloses the summary fields returned (id, name, type, crs, public source), but does not state that the operation is read-only, whether results are paginated, or what permissions are needed. The return-field hint is useful but insufficient for a tool with zero annotation coverage.

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, front-loaded fragment with no wasted words. It is efficient, though its terseness contributes to the missing usage and behavioral context.

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 listing tool with no output schema and no annotations, the description gives the scope and return fields, which is adequate. It still leaves gaps around how it relates to inspect_layer and whether the listing is safe/read-only.

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 has zero parameters, so the baseline is 4. The description does not need to explain any 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?

The description names a specific resource and scope ('Layers in the current project') and lists the fields returned, which is more informative than a tautology. However, it is a noun phrase rather than an explicit verb+resource statement, and it does not distinguish itself from sibling tools like inspect_layer or add_layer beyond the implied listing 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 provides no when-to-use guidance, no exclusions, and no mention of alternatives. An agent must infer that this is the bulk-listing counterpart to inspect_layer.

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 only implies read-only via the name and mentions two returned fields. It says nothing about scope (all installed plugins vs. those enabled for the current user/workspace), ordering, or whether the operation has any side effects.

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 short sentence with no filler, and the key attribute (active state) is front-loaded. It is a sentence fragment rather than a complete statement, but 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?

For a zero-parameter list tool with no output schema, the description conveys the rough shape of the return value (versions and active flags). It still leaves scope and enumeration completeness unstated, which is the main thing an agent would want to know before relying on the result.

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 disambiguate; baseline 4 applies. No parameter-level confusion is possible.

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 fragment names the resource (plugins) and the returned attributes (version, active state), and the name supplies the "list" verb. It stops short of an explicit verb+object statement and does nothing to distinguish it from siblings like reload_plugin, which operate on the same resource.

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 indication of when to call this versus reload_plugin or any other plugin-related sibling, no prerequisites, and no exclusion conditions. The agent must infer usage entirely from the tool name.

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 conveys that the scope is fixed to the 'configured recipe directory' (no parameter to change it), but says nothing about ordering, recursion into subdirectories, whether docstrings can be missing/empty, error behavior if no directory is configured, or output size limits.

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 front-loaded sentence with the returned fields parenthesized inline. Nothing extraneous and nothing buried.

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 zero-parameter read tool with no output schema, the description covers what is returned at a high level (name + docstring), but leaves gaps on result ordering, docstring absence, and failure modes that an agent may need when deciding what to do with the output.

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. The description correctly frames the directory as configured rather than caller-supplied, which prevents an agent from looking for a path argument.

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?

Specific verb (List) plus resource (recipe files) with an extra detail on the returned payload (name + docstring). It is clear what the tool does, but it never distinguishes itself from siblings like run_recipe or list_algorithms, so the agent must infer that this is the discovery step rather than the execution step.

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: listing recipes in the configured directory suggests a discovery-before-run_recipe workflow, but the description never states when to use this rather than run_recipe or how to act on the results. No exclusions or prerequisites 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?

With no annotations, the description carries the burden, and it does disclose scope: top-level windows only, plus the active modal window. However it says nothing about ordering, whether this is a safe read (implied by 'List'), snapshot behavior, or how hidden windows are treated.

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?

One tightly packed sentence: verb first, resource second, output fields parenthesized, and the extra modal-window behavior appended. No filler at all.

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 exists, yet the description enumerates what each result entry contains, which is the main thing an agent needs. The remaining gap is the undocumented include_hidden flag and the absence of any behavioral/safety detail that annotations would normally supply.

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% and the single boolean include_hidden is never mentioned in the description, so an agent gets no guidance on how it affects the listing. Mitigating factor: one self-descriptive boolean with default false, so the omission is minor rather than crippling.

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+resource ('List top-level windows') and even enumerates the returned fields (objectName, title, class, geometry, modal) plus the active modal window. It doesn't explicitly contrast with siblings like dump_widgets or close_window, so the agent must infer the boundary.

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 statement of when to use this versus alternatives such as dump_widgets (which likely returns a deeper widget tree) or close_window. Usage is only implied by the resource name.

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 the return payload (version, mode, pid), which is real information given the empty input schema and absent output schema, but it never states that the call is read-only and side-effect free.

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 front-loaded sentence with zero filler: purpose first, return values second. Every clause 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?

For a trivial no-argument connectivity probe with no output schema, the description supplies enough to call it correctly and know what comes back. Only the missing read-only/safety statement keeps it short of complete.

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 per the baseline rule a 4 applies; there is nothing for the description to disambiguate beyond the documented return fields.

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 gives a specific verb ('Check connectivity') plus the exact payload returned (plugin version, mode, QGIS pid), which clearly separates it from diagnostic siblings like get_info or read_log. It is not a tautology of the name 'ping'.

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 implied by 'Check connectivity' and the nature of a ping, but there is no explicit statement of when to prefer it over get_info or read_log, nor any precondition or exclusion. Adequate but leaves routing 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 burden. It usefully discloses the log window (entries since probe load) and that incremental polling is supported, but it says nothing about ordering (newest vs oldest first), what limit does by default, or whether the read is non-destructive/cheap.

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 filler, with the resource scope front-loaded and the polling tip second. Nothing here could be cut without losing 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?

For a 5-parameter tool with no annotations and no output schema, the description is thin: it covers one parameter and the time bound but leaves the filter semantics and the shape of returned entries (fields, ordering, truncation by limit) 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% across 5 parameters, so the description must compensate and it only explains since_id. The meaning and expected values of tag, level, contains, and limit are left entirely undocumented.

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 gives a specific verb+resource: it reads QGIS message-log entries, and it bounds the scope to entries captured since the probe was loaded. That is enough for an agent to distinguish it from widget/layer/algorithm siblings, though it never explicitly contrasts with any of them.

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?

One concrete usage pattern is supplied: use since_id to poll for new entries. There is no guidance on when to use the other filters, no mention of alternatives, and no statement of when this tool is not appropriate, so usage is implied rather than fully specified.

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 destructive sequence (unload and module purge), which implies in-memory state loss. It says nothing about permissions, what happens to registered widgets/actions tied to the plugin, or failure behavior for an unknown name.

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?

One sentence, action front-loaded, with the exclusion as a compact parenthetical. No filler.

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 single-parameter, no-output-schema tool the description covers the what and the when, but leaves the only parameter's expected value and the post-reload state of dependent UI elements unexplained. Adequate, not complete.

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?

Only one parameter at 0% schema description coverage. The phrase "reload a plugin" and the qgis_dev_probe exclusion imply that `name` identifies the plugin, but the description never states the expected format or whether it is a short name vs module path.

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?

Precise verb chain (unload, purge modules, reload) applied to a specific resource (a plugin), plus the rationale that code edits take effect. It's clearly not one of the read-only siblings like list_plugins, though it doesn't name a direct 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?

States the trigger condition ("so code edits take effect") and an explicit exclusion ("not for qgis_dev_probe itself"), which is genuine when/when-not guidance. No named alternative tool is given, but the exclusion prevents a specific miscall.

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 doesn't state whether removal is permanent/undoable, what happens if the layer doesn't exist, or whether permissions or unsaved changes affect it — significant gaps 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?

One short sentence, verb-first and front-loaded, with no wasted words. Slightly under-specified rather than bloated.

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 destructive mutation with no annotations and no output schema, the description omits irreversibility, failure modes on unknown layers, and return/confirmation behavior.

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%, but the description compensates partially by clarifying the single 'layer' parameter accepts either an id or a unique name. It stops short of describing id/name format or matching behavior.

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 (remove a layer) and adds the lookup key ('by id or unique name'). It is reasonably distinguishable from siblings like add_layer and list_layers, though it doesn't explicitly name them.

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?

No indication of when to use this versus alternatives such as add_layer or inspect_layer, and no prerequisites or exclusions. The purpose is inferable but no routing guidance is 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?

With no annotations, the description carries the full burden. It usefully discloses that execution is synchronous and blocks the UI, and that results plus a log are returned, but it says nothing about timeout behavior, error handling, or whether a failed run leaves partial state — gaps that matter for a 600s default timeout 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?

Three short sentences, front-loaded with the action and mode, with no filler. It is tight, though the brevity contributes to the semantic gaps noted elsewhere.

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?

It covers return values adequately ('results and the log') so an output schema isn't required, but for a tool with a nested free-form argument and no annotations, the absence of parameter format guidance and timeout/failure semantics leaves the definition short of complete.

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 the description explains none of the three parameters. The critical details — the expected format of algorithm_id (e.g. provider:name) and the shape of the free-form nested 'parameters' object — are undocumented in both places, and timeout_s is never mentioned.

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 ('Run a Processing algorithm') plus the execution mode ('synchronously'), which is more than a name restatement. It does not explicitly contrast with siblings like run_recipe or execute_code, so sibling differentiation is left to inference.

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 blocking warning ('QGIS UI is blocked meanwhile') implies this should be used deliberately, but there is no explicit when-to-use / when-not-to-use guidance and no pointer to run_recipe or get_algorithm_params as the discovery path for algorithm_id.

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 at all, the description carries the full disclosure burden. It hints at arbitrary code execution by naming the Python entry point, but says nothing about side effects being permanent, permission/auth requirements, what happens on timeout, or what the call returns.

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 front-loaded sentence with zero wasted words. It is efficiently written, but the brevity comes at the cost of leaving the operational detail absent rather than being an example of tight completeness.

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 that executes arbitrary Python with no annotations, no output schema, and 0% parameter documentation, this description is too thin. An agent cannot tell whether execution is sandboxed, how failures or timeouts surface, or how `args` is interpreted by the target recipe.

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 three parameters. The description implies `args` is forwarded to the recipe's `run(ctx, args)` call, which is genuinely useful, but `name` (must match a file in the recipe directory) and `timeout_s` (default 600, and the consequence of exceeding it) get no explanation anywhere.

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 ("Run a recipe") and defines what a recipe is ("a Python file with `def run(ctx, args)`") and where it lives (the configured recipe directory). That is enough to separate it from run_algorithm or trigger_action, though it never names a sibling 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 pick this over execute_code or trigger_action, nor any note that a recipe name should first be discovered via list_recipes. The agent must infer usage entirely from the one-line purpose statement.

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 a valuable side effect — the image is written to disk and a path returned ('plus its saved path') — but omits where files are saved, naming/overwrite behavior, and whether capture requires the window to be visible or active.

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 tight sentences with the capability first and the return value second; no filler, nothing buried.

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 exists, and the description does cover the return value (PNG plus path), which is a plus. But for a three-parameter, zero-annotation tool with 0% schema coverage, the missing parameter-to-mode mapping and disk-write details leave real 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 description coverage is 0%, so the description must compensate. It hints at 'window' and 'object_name' through the target list, but leaves 'name' (presumably the output filename) completely unexplained and never states which arguments are mutually exclusive or combinable.

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 gives a specific verb ('Capture') and names three concrete targets (QGIS main window, a window, one widget), plus what it returns. It is clearly distinguishable from siblings like list_windows or dump_widgets, though it never maps the three targets to the three parameter names.

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 explicit guidance on when to use this tool, which parameter combination selects which capture mode, or what the defaults do when all three arguments are omitted (all are optional). The three targets are listed but not tied to any selection rule, so the agent must guess.

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 discloses refusal conditions for invisible, disabled, and read-only widgets, but it omits mutation side effects, return behavior, and error handling beyond refusal.

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 compact and front-loaded, with the core action stated first and the refusal constraint second. The trailing ellipsis in the value list is slightly vague but does not bloat the description.

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 mutation tool with no annotations, no output schema, and 0% schema description coverage, the description is incomplete. It should clarify how window/object_name/index identify the target and what happens on success or failure.

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 for four undocumented parameters. It hints at value types but does not explain 'window', 'object_name', or 'index', leaving most parameter semantics unclear.

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 and resource: 'Set a widget value', and lists accepted value categories (text, number, bool, combo index/text). It is clearly different from read-oriented siblings like read_log or dump_widgets, though it does not explicitly contrast with click_widget or trigger_action.

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 gives a behavioral constraint ('Refuses invisible/disabled/read-only widgets') but does not say when to choose this tool over alternatives such as click_widget or trigger_action. There is no explicit when-to-use or prerequisite 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 and does well: it discloses that the trigger is deferred while the reply is immediate, so a modal dialog will not block the caller — a non-obvious and important trait. It also discloses refusal conditions (submenus, disabled actions). It stops short of saying what a refusal or failure looks like in the response.

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 sentences, front-loaded with the identification strategy, then the async behavior, then the failure modes and verification hint. No filler.

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 and no annotations, so the description is the only documentation; it covers behavior and two of four parameters but omits index/window semantics and the shape of success/failure replies. Adequate to attempt a call, not complete.

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. It adds real meaning for 'object_name' (preferred identifier) and 'text' (mnemonic '&' ignored), but leaves 'index' and 'window' completely unexplained — the reader cannot tell whether index disambiguates duplicate matches or that window defaults to the QGIS main window.

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 (trigger) and resource (a QAction), plus the two addressing modes (objectName preferred, or visible text with '&' mnemonics ignored). This cleanly separates it from click_widget, which operates on widgets rather than QActions.

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 an explicit preference ordering (objectName preferred over visible text) and states hard exclusions: submenus and disabled actions are refused. It also names follow-up tools (list_windows / screenshot) for verifying the outcome, though it never explicitly contrasts itself with click_widget or list_actions.

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 disclosure burden. It usefully states the blocking sleep behavior and the 60-second ceiling, but leaves open whether a value over 60 errors or is clamped, and whether the call blocks the whole session or just the agent loop.

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?

One sentence, front-loaded with the verb and the hard constraint, then the rationale. Nothing is padded and nothing important is buried.

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 trivial one-parameter timing tool with an output schema present, the description covers what the tool does, why, and its safety ceiling. The only real gap is the over-limit behavior, which is minor for this complexity level.

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 single 'seconds' parameter is undocumented in the schema apart from a default of 1. The description partially compensates by stating the 'max 60 s' bound, but it never names the parameter or says what unit granularity (fractional?) is accepted.

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 gives a specific verb ('Sleep') plus the reason it exists: letting deferred GUI actions finish before the next observation. It is unambiguous and clearly distinct from action-oriented siblings like click_widget or trigger_action, though it doesn't explicitly contrast itself with them.

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?

'...so deferred GUI actions can finish before the next observation' tells the agent the situation that selects this tool: an observation follows an action that needs time to settle. No exclusion or alternative is named, but none is really needed for a single-purpose sleep tool.

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