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

No annotations are provided, so the description must disclose behavioral traits. It only states the click action, omitting side effects, post-click behavior, error handling, or whether it waits for the element.

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 front-loaded sentence with illustrative examples; no filler. Efficient and easy to parse.

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

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

For a simple click tool with no output schema, the description covers purpose and parameter examples. However, with no annotations, it lacks behavioral details an agent might need to invoke correctly, such as what happens after 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?

The schema fully documents both parameters, but the description adds concrete examples of button text values for the 'name' parameter, which helps an agent pick appropriate values. It does not explain the 'exact' parameter, which remains schema-only.

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 (click) and resource (a button found by display text), with concrete examples of button labels. It clearly distinguishes from sibling tools that set checkboxes or fill fields, though it does not explicitly name an 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?

No indication of when to use this tool versus siblings like jizura_set_checkbox or jizura_fill, nor any prerequisites or exclusions. The examples illustrate parameter values, not usage contexts.

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 states the session is terminated but says nothing about side effects—whether unsaved data is lost, what happens to open pages, auth requirements, or reversibility. For a terminal/close-style action this is a meaningful 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 front-loaded sentence with no filler, so nothing needs trimming. It is appropriately minimal for a zero-parameter action, though equally terse.

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 0-param, no-output-schema tool, the description covers the core purpose. However, the one thing an agent most needs before closing a session—side effects such as lost unsaved state—is absent, leaving it just adequate.

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

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

The tool takes zero parameters, so the baseline is 4. The description correctly implies no parameterization is needed, and there is no schema surface left 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?

State a specific verb (終了する = terminate) and resource (JIZURA browser session), so an agent knows exactly what the tool does and can distinguish it from its counterpart jizura_open. It stops short of explicitly contrasting itself with that sibling, but the action is unambiguous.

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

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

Usage is only implied: the agent can infer it should be called when done with the browser session, and that jizura_open is the inverse. There is no explicit when-to-use statement, no prerequisites, and no note on whether other session tools must be called 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?

With no annotations, the description carries the full burden. It usefully discloses the async flow (press, wait for download, save locally) and that it writes to a local path, but it omits critical behavioral details such as overwrite semantics for savePath, timeout/error handling, and what happens if the export button is unavailable.

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 action sequence and followed by the critical buttonName enumeration. There is no wasted phrasing, and the structure directly supports correct invocation.

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 UI-automation export tool with no annotations, no output schema, and only 50% schema description coverage, the description covers the core flow and the required buttonName values. However, it lacks essential context about failure modes, return behavior, and savePath overwrite semantics, so it is only minimally 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 coverage is 50%: savePath has a schema description, but buttonName has none and no enum. The description compensates for buttonName by enumerating the three valid values ('MP4 を書き出す', '連番PNG（ZIP）', '透過PNG（ZIP・背景なし）'), which is a meaningful addition. It does not add constraints or format details for savePath beyond what the schema already says.

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: press the export button, wait for the download, and save it locally. It is clearly an export operation and distinguishes itself from primitive UI siblings like jizura_click by describing the full save workflow, though it does not explicitly contrast itself with those siblings.

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

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

The description explains the mechanical steps but gives no guidance on when to use this tool versus alternatives, no prerequisites, and no exclusions. It does not state, for example, that it should be used instead of jizura_click when a download is expected.

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 full behavioral burden. It usefully discloses the locating mechanism (label or placeholder), but says nothing about failure behavior when no field matches, whether existing values are overwritten, or whether input events are dispatched.

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 that states the mechanism first and appends examples. Efficient with no wasted wording, though it could not be shorter without losing the field-locating 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 two-parameter UI automation tool with no annotations and no output schema, the description covers the core action and target fields but omits error/edge behavior and interaction side effects, leaving meaningful gaps for an agent.

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. It partially does: 'name' is implied to be the label/placeholder identifier and 'value' is illustrated with examples, but exact-match semantics and format expectations remain unstated.

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 ('find the input field by label or placeholder and enter a value') and gives concrete examples (BPM, start seconds, file name). It is distinguishable from siblings like jizura_set_checkbox and jizura_click, though it never names 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?

Usage is implied by the field-locating mechanism (label/placeholder), but there is no explicit when-to-use guidance, no mention of prerequisites, and no routing against alternatives such as jizura_set_checkbox or jizura_set_lyrics.

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 disclosure burden. It mentions the button mechanism but omits what happens on invalid files, whether the current track is replaced, permission needs, or UI side effects like opening a file dialog.

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, efficient sentence with the action and mechanism front-loaded. It is appropriately sized for the tool's simplicity, though it could benefit from one more clause about prerequisites.

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 tool is simple and the schema is complete, with no output schema needed. However, for a UI automation tool the description omits prerequisite state such as whether jizura_open must be called first, leaving a minor gap in context.

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 are already documented in the schema. The description adds no additional meaning about filePath or buttonName beyond what is structurally provided, making the baseline 3 appropriate.

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

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

States a specific verb and resource: loading a local audio file via the named button. This distinguishes it from generic siblings like jizura_click or jizura_fill, though it does not explicitly name an 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?

Provides no when-to-use or when-not-to-use guidance. It only says what the tool does, leaving the agent to infer context such as whether the app must be open first or whether this replaces the current audio.

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 the behavioral burden. It discloses the browser engine (Playwright Chromium) and that the call establishes a stateful, manipulable session, which is meaningful. However it omits whether calling it twice is safe, whether the session must be cleaned up via jizura_close, and any failure/rate-limit behavior — notable gaps for a state-establishing 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?

Two short sentences with zero filler: the action/URL comes first, the prerequisite-ordering rule second. Nothing could be removed 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?

No output schema and no annotations, but for a session-opener the description covers what the agent needs: what is opened, how, and when to call it. Minor gap: the session lifecycle (repeated calls, cleanup via jizura_close) is left to inference from sibling names.

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 only one parameter (headless) and the schema documents it at 100% coverage, including the default (false = visible window). The description adds nothing about it, so the baseline of 3 applies.

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 ('開き' / open) plus the exact target resource (the JIZURA URL loaded via Playwright Chromium) and the effect ('操作可能なセッションを開始する'). This clearly separates it from the action siblings (click, fill, snapshot), which operate on an already-open session.

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

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

Explicitly states the prerequisite ordering: '他のjizura_*ツールを使う前に一度呼ぶ' (call once before using the other jizura_* tools). It does not state any when-not condition or mention jizura_close as the lifecycle counterpart, but the invocation context is unambiguous.

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 it does disclose the output format (PNG). However it says nothing about scope of 'current screen', whether it requires the window to be open/focused, or latency/cost considerations for a capture 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?

Two short sentences with zero waste: the operation is front-loaded, followed immediately by the trigger condition. Every sentence earns its place.

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

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

For a zero-parameter, no-output-schema tool the description covers what it does and when to use it. The one real gap is disambiguation from jizura_snapshot, which an agent in this family of tools 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?

The tool takes zero parameters, so there is nothing for the description to compensate for; the baseline of 4 applies. No parameter-related meaning is missing.

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 concrete verb and resource: captures the current screen as a PNG image. That is specific and actionable, but it does not distinguish itself from the similarly named sibling jizura_snapshot, which an agent could reasonably confuse with a screen-capture operation.

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 usage condition: use it when you want to visually confirm the arrangement result. That is clear context for when to call it, though it names no exclusions or alternatives (e.g. snapshot vs screenshot) to disambiguate the sibling tools.

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

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

No annotations are supplied, so the description carries the full disclosure burden for a mutation tool. It does not state idempotency, what happens if the label name is not found, whether the change persists across snapshot/export, or error behavior for an invalid label.

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?

Compact and front-loaded: the action and its key are stated first, followed by examples. No filler, though the examples occupy most of the length without adding usage or parameter-constraint 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 two-parameter mutation with no annotations and no output schema, the description is minimally adequate — it says what it does and gives target examples. It omits error/failure semantics and any indication of how to obtain valid label names, which matters since the labels are UI-dependent.

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 does clarify that 'name' is a label name (not a free-form key) and gives three concrete example labels, and that 'checked' corresponds to ON/OFF. That covers both parameters at a basic level, but gives no format/length/constraint details or how labels are discovered.

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 (設定する/set) and resource (チェックボックスのON/OFF) plus the selection key (ラベル名). An agent can tell what it does, but nothing distinguishes it from sibling tools like jizura_click or jizura_fill, which could plausibly also target UI toggles.

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?

Provides example label names, which hints at intended targets, but never says when to use this versus jizura_click/jizura_fill, nor any prerequisites (e.g., that the label must already exist in the current UI). No when/when-not 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 full behavioral burden. It discloses how notation affects visual output (e.g., *emphasis* enlarges and brings forward, ~whisper~ shrinks), which is useful. However, it does not state whether existing lyrics are overwritten or appended, whether an open session is required, or any auth/permission needs. Core mutation semantics remain undisclosed.

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 front-loaded with the tool's action, then presents a well-organized bullet list of notation rules. Every line defines a distinct notation element or an escape rule, so the length is justified by the tool's domain-specific input format. There is no filler or redundancy.

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

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

For a tool whose main complexity is the custom input notation, the description is highly complete: it thoroughly documents the parameter format. However, it omits any statement about mutation behavior (replace vs. append existing lyrics) or session prerequisites. Without annotations or an output schema, that missing behavioral context keeps it from being fully 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 coverage is 100%, but the schema description only says 'JIZURA記法済みの歌詞テキスト' (lyrics text in JIZURA notation). The description provides an extensive notation reference defining cuts, overlays, emphasis, timestamps, escapes, and more—far beyond what the schema conveys. This is exactly the additional meaning the parameter dimension rewards.

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 clear verb and resource: '歌詞入力欄にJIZURA記法のテキストを流し込む' (pour JIZURA-notation text into the lyrics input field). This is specific enough for an agent to understand it sets lyrics, but it does not explicitly differentiate from sibling tools like jizura_fill, which also fills input fields. No alternative or exclusion is named.

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 input-preparation guidance: convert natural-language instructions (e.g., 'make the chorus emphasized') into the JIZURA notation before passing. This implies when to use the tool (when you have lyrics or instructions to render), but it never states when to choose this tool over siblings or any preconditions/exclusions. Usage is only implied.

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 that it returns a list of names for currently displayed operable elements. However, it does not explicitly state read-only/non-destructive behavior, rate limits, or how the optional limit affects the result set.

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 tightly written sentences. The return value and scope come first, followed by the intended use case, with no redundant or wasted wording.

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 snapshot tool, the core return and usage are covered. But the description leaves the limit parameter unexplained and does not describe the return structure beyond “list of names,” which is a gap given no output schema and no annotations.

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

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

The only parameter, limit, is undocumented in both the schema and the description. The description does not explain what limit controls, its default, or its interaction with the returned list, so it adds no semantic meaning beyond the schema’s type and 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?

States a specific verb and resource: returns a list of names/labels for currently displayed operable elements such as buttons, checkboxes, and text inputs. It also names the sibling tools (jizura_click, jizura_set_checkbox, jizura_fill) it feeds, making its role distinct from screenshot or interaction tools.

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

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

Explicitly states the usage context: use it to check or adjust the name passed to jizura_click, jizura_set_checkbox, and jizura_fill. It does not state when not to use it or contrast it with jizura_screenshot, but the intended workflow is clear.

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