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

With no annotations, the description carries the full burden of behavioral disclosure. It does explain what the changelog contains and what data accompanies each item, but it never explicitly states whether this is a read-only retrieval operation, whether it returns a list, or what side effects, if any, might occur.

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 dense sentence with no filler. The core subject is front-loaded, and the parenthetical list plus trailing data fields earn their place by conveying scope and expected content efficiently.

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

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

For a zero-parameter tool, the description covers the main data categories well, but it omits an explicit action verb and any guidance on how the returned changelog relates to sibling workflows. Since there is no output schema, the description should more clearly state what invoking the tool returns.

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 and the schema covers 100% of them, so the description does not need to explain parameter meaning. It adds value by describing the content fields that will come back, though that is more about output than parameters.

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

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

The description clearly identifies the resource: Figma changes that need an LLM to finish in code, including specific categories and attached data. It does not use an explicit verb like 'list' or 'retrieve,' so it stops short of a fully specified action, but the intent is unambiguous from the name and content description.

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 versus alternatives such as jev_list_pending or jev_resolve_pending. The phrase 'anything the rules and Jev could not write' implies a boundary, but the description does not state when an agent should choose this changelog over 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?

With no annotations, the description carries the behavioral burden. It clearly signals that this is an informational reference table rather than a mutating operation, but it does not explicitly state that invoking the tool causes no side effects or describe the return format.

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, tightly written sentence that front-loads the resource and then specifies the key information about sync direction. Every word contributes useful meaning and there is no redundancy.

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

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

Given the tool's simplicity (no parameters, no output schema), the description covers the core purpose and content well. It could be slightly more complete by explicitly stating what a caller receives upon invocation, but that is a minor gap for an informational reference tool.

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

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

The tool has zero parameters, so there is no parameter information the description needs to add. The baseline of 4 applies, and the description adequately explains the tool's focus without needing to compensate for schema gaps.

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 identifies a specific resource: the CSS↔Figma property table, and states the content it exposes (which direction each property syncs). This makes it clearly distinct from sibling tools like jev_sync_now or jev_status, though it lacks an explicit action verb such as 'returns' or 'lists'.

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

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

The description implies the tool is used to look up the supported property mapping and sync direction for the CSS↔Figma integration. It does not explicitly state when to use this tool versus alternatives, nor does it provide any exclusions or conditions.

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 burden of behavioral disclosure. It usefully explains that the input is an async function body with `figma` in scope and that the return value must be JSON-serializable, but it does not disclose potential side effects, destructive document changes, error behavior, or permission implications of executing arbitrary code.

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 compact sentence that front-loads the core idea ('Escape hatch') and packs all necessary constraints into a small amount of text. Every clause earns its place, with no filler or redundant repetition of the tool name.

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

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

For a tool with no output schema, no annotations, and a single undocumented parameter, the description provides the essential invocation contract: input format, execution context, and return serialization. However, it omits error handling semantics, side-effect warnings, and any indication of what happens on invalid or non-serializable returns, leaving noticeable gaps for an arbitrary-code execution tool.

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

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

The input schema only describes `code` as a string with 0% description coverage, so the description must compensate. It does by explaining that the code is an async function body, runs inside the plugin with `figma` available, and must return a JSON-serializable value, which adds meaningful meaning beyond the raw schema type.

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 action ('run Figma plugin API code') and a specific resource/context ('inside the Jev Bridge plugin'). It also frames itself as an 'escape hatch', which clearly distinguishes it from the more specialized sibling tools by presenting it as the generic fallback for arbitrary code.

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 term 'escape hatch' gives clear contextual guidance that this tool is for cases where the dedicated sibling tools do not apply. It does not explicitly name alternatives or exclude conditions, but the implication is strong enough for an agent to infer when to use it.

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 disclosure burden. It does convey what items appear and that each includes a reason, but it does not explicitly state that the operation is read-only or describe the output format. For a list tool this is a moderate gap rather than a serious one.

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 short and front-loads the main subject while adding a meaningful qualifier about reasons. It would be slightly stronger with an explicit verb like 'Lists,' but there is no unnecessary content.

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 no-parameter read-oriented listing tool with no output schema, the description covers what is listed and why each item is pending. It omits output-structure details and sibling routing, but those are not essential at 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?

The tool has zero parameters, so the schema provides complete coverage and the description has no parameter-level burden. The description still usefully characterizes what domain concept the tool returns.

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 the specific resource ('Figma edits that were not written to code automatically') and the key detail (the reason for each item). It is clear in meaning, but the noun-phrase structure relies on the tool name for the verb and it does not explicitly distinguish from siblings like jev_status or jev_changelog.

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 implies the tool is the place to inspect unresolved Figma edits, especially those involving uncertain placement or design tokens. However, it never states when to choose this over jev_status, jev_progress, or jev_changelog, nor does it mention follow-up actions like jev_resolve_pending.

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 of conveying the operation's behavior. 'Find' clearly signals a read-only lookup, and it names what is returned (source file and line). It does not explicitly mention error behavior when no match is found, but for a simple locate tool this is a reasonable level of disclosure.

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

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

The description is a single sentence that front-loads the action and target, includes a helpful example, and contains no filler. Every word contributes to understanding.

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

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

Given the tool's simplicity—one required parameter, no output schema, no annotations—the description covers the essential facts: what it locates, the input format, and the kind of result. It is sufficiently complete for an agent to invoke it correctly.

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

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

Schema description coverage is 0%, so the description must compensate. It does by explaining that `code` is a 'Figma layer code' and providing a concrete format example (@a3.0.2.1). This adds meaning beyond the raw string type in the schema, though it could be more precise about allowed formats.

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 ('Find'), a precise resource ('source file and line'), and a clear input ('Figma layer code') with an illustrative example. This makes the tool's purpose unmistakable and distinguishes it from the sibling sync/execution tools.

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

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

The description implies when to use the tool: when you have a Figma layer code and need its source location. However, it does not explicitly contrast this with sibling tools like jev_execute or jev_sync_now, nor does it state when not to use this tool.

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

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

With no annotations, the description carries the full burden. It discloses the key side effect for done:true (Figma redrawn, changelog cleared), but does not explain what happens when done:false or the nature of the progress report itself (e.g., whether it persists state or just displays text). Partial transparency, not complete.

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

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

Two sentences with zero filler. The first sentence establishes purpose and context; the second adds the critical done:true behavior and consequences. Information is front-loaded and every phrase 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 simple 2-parameter tool with no output schema and no annotations, the description covers the main flow but leaves 'text' semantics and the done:false behavior unexplained. An agent can call it correctly for the completion case, but may be unsure what to pass for intermediate steps.

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 gives clear semantics for 'done' (true means all items fixed) and the overall action implies 'text' is the step content, but it never explicitly describes what text should contain or how it is displayed. One of two parameters is adequately explained.

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 action ('report a step') and target ('designer's Figma panel') with a clear trigger context ('During a Fine-tune'). It distinguishes the tool from siblings by its progress-reporting role, though it doesn't name any alternative explicitly.

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

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

Gives explicit when-to-use context ('During a Fine-tune') and a specific condition for done:true ('when every item is fixed'). It lacks explicit when-not-to-use guidance or named alternatives, but the context is clear enough for an agent to select this over status/sync 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 present, so the description carries the full behavioral burden. It does add useful context: it creates auto-layout frames/components, enables live two-way sync, and requires a running dev server. However, it does not disclose side effects on existing Figma screens, whether the operation is reversible, or that live sync persists until stopped.

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

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

The description is two sentences with no filler. The main action and output format are front-loaded, and the prerequisite and trigger phrase are delivered efficiently. 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 six-parameter tool with no output schema and no annotations, the description is adequate but thin. It covers purpose, trigger, and prerequisite, but omits what the tool returns, how live sync can be stopped, and how this tool relates to siblings like jev_sync_now and jev_stop_live.

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%, and each parameter already has a meaningful description. The tool description adds no new parameter-level semantics beyond reinforcing the dev-server prerequisite, so the baseline score of 3 is appropriate.

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

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

The description states a specific action ('Push the app's screens into Figma'), a concrete output shape ('auto-layout frames and components'), and a distinguishing behavioral feature ('live two-way sync'). The trigger phrase 'push to Figma' also makes it easy for an agent to recognize when this tool is intended.

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 clear usage context: call it when the user says 'push to Figma' and only when the dev server is running. It does not explicitly mention when not to use it or name alternatives like jev_sync_now or jev_stop_live, so it falls short of a full 5.

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

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

The description discloses the behavior of each action: 'apply' writes, 'reject' drops, 'element/token' choose scope, 'llm' hands off, 'done' marks finished and triggers redraw. This is comprehensive for a decision tool, but it doesn't mention side effects like irreversibility or error conditions. Given no annotations, the description carries the full burden and does so adequately.

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 sentence that front-loads the purpose and then lists each action compactly. Every part contributes to understanding, with no fluff.

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

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

The description covers all actions and their outcomes. It does not describe return values, but that is likely irrelevant for a decision tool. It doesn't mention prerequisites like whether the item must exist, but that is a minor omission. Overall, it is sufficiently 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 schema has 0% description coverage, so the description must explain the parameters. It does explain the 'action' parameter by detailing each enum value's meaning. However, the 'id' parameter is not explicitly described, though it is implied as the pending item identifier. The description adds value over the schema by clarifying the semantics of the actions.

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

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

The description clearly states the tool's purpose: 'Decide a pending item' and enumerates the actions with their outcomes. It is specific and unambiguous, though it doesn't explicitly differentiate from sibling tools like jev_list_pending, but the purpose is clear.

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

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

It explains when to use each action (e.g., 'apply' when you want to write the best guess), but it doesn't explicitly state when to use this tool versus alternatives. The context of pending items is implied but not contrasted with other tools. It provides no exclusions or alternative references.

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

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

With no annotations, the description carries the full burden. It does name the components whose status is checked and implies a read-only observation, but it does not explicitly say it is non-mutating or describe possible outcomes, partial failures, or the shape of the status report. This is adequate for a status tool but not fully transparent.

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

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

The description is a single compact sentence that front-loads the core concept ('Connection status') and then lists the relevant components. There is no filler, repetition, or unnecessary context; every phrase adds 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 zero-parameter status query, the description gives the essential context: what is being checked and at what level. However, since there is no output schema and no annotations, it leaves the return representation and failure behavior unspecified, so an agent cannot fully anticipate what the tool will return beyond a generic status indication.

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 description has essentially no parameter-semantics burden. The empty schema already covers everything, and the description sensibly avoids inventing input details. This matches the baseline for parameterless tools.

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

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

The description clearly identifies the resource as 'connection status' and enumerates the exact scopes checked: the Figma plugin, the backend, and the live session with screens and pending reviews. It stops short of an explicit verb like 'get' or 'report,' but the intent is unambiguous and the specificity separates it from most sibling tools.

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

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

The intended use is implied: call this tool when you need to know whether the Jev Bridge plugin, backend, and live session are connected. However, there is no explicit when-to-use guidance, no mention of alternatives, and no note about whether it should be a first diagnostic step before other Jev operations.

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

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

With no annotations provided, the description carries the behavioral burden, and it does disclose the main effects: it stops file watching and closes the headless browser, while explicitly noting that Figma layers are preserved. It does not mention idempotency, auth requirements, or what happens if no live session is active, so full transparency is lacking.

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 focused sentence with the main action front-loaded and a useful clarification about Figma layers. Every phrase earns its place, with no wasted words.

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

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

For a zero-parameter, no-output-schema stop command, the description tells the agent what will stop and what will be preserved, which is the key context needed to decide to call it. It could add a note about whether calling it when no session is running is safe, but the core use case is covered.

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 schema already fully covers parameter semantics; the 0-parameter baseline of 4 applies. The description appropriately adds no parameter details because there are none to document.

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 action ('stop the live session') and immediately specifies what that entails: stop watching files and close the headless browser. This clearly distinguishes it from sibling tools like jev_sync_now or jev_status, which are not stop operations.

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 intended use is clear: call this when the live session should be ended, since the description defines the live session's active behavior as watching files and running a headless browser. It does not explicitly name alternatives or when-not-to-use, but no other sibling tool performs this stop function.

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 of behavioral disclosure. It conveys that the tool returns recent edits and identifies the deciding actor, which is useful, but it does not mention ordering, the default number of entries, or whether the operation is read-only. For a log-style tool this is adequate but not rich.

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 compact sentence that front-loads the core purpose and enumerates the returned information with no filler. Every segment adds value.

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

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

The description covers the main return content and makes the tool's general purpose understandable. However, with no output schema and no annotation coverage, it omits practical details such as the meaning of limit, result ordering, and whether anything is modified, leaving a few gaps an agent would need to resolve.

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, has 0% schema description coverage, and the description never mentions it. The word 'recent' hints at a limited window, but the description does not explain how limit controls the result set, so it fails to compensate for the missing schema guidance.

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

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

The description clearly identifies the resource as a log of recent Figma-to-code edits and lists the key output fields (what changed, file, line, decision maker). It lacks an explicit verb like 'retrieve' or 'list', and does not distinguish itself from the similarly named sibling jev_changelog, so it is clear but not fully differentiated.

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 is given for when to use this tool versus alternatives like jev_list_pending or jev_changelog. The description implies it is for checking recent edit history, but it does not state conditions, exclusions, or how it differs from sibling tools, leaving the agent to infer applicability.

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 itself must disclose side effects, and it does: it states that writing all queued edits into code and refreshing every Figma screen from code both occur. It is transparent about scope ('all queued', 'every screen') and about the fact that both code and Figma are mutated. It does not mention reversibility, permission requirements, or failure modes, but for a zero-parameter action the core behavioral contract is clear.

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 entire description is one sentence with a colon splitting the action into two understandable clauses. It is front-loaded with the key idea ('One-click sync') and contains no filler or 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 zero-parameter action this is largely complete: it says what will be written and what will be refreshed, and there is no output schema to document. The main gaps are the lack of any indication whether the operation is asynchronous, how success is reported, or what happens if the queue is empty. These are minor for a one-click sync but prevent a perfect score.

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

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

The input schema is empty, so the baseline for zero parameters is 4. The description reinforces the no-input nature with 'One-click' and uses 'all queued' and 'every screen' to make clear there is no subset selection. No additional parameter-level detail is needed.

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

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

The description opens with 'One-click sync' and then specifies the exact bidirectional effect: queued Figma edits are written into code, then every Figma screen is refreshed from code. This is a specific verb-plus-resource statement that differentiates it from one-way siblings like jev_push_screens or investigation tools like jev_list_pending.

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 'use when' or 'do not use' language and no reference to alternatives, so an agent must infer that this is the catch-all synchronization command. The phrase 'one-click' implies it is the single command to reconcile Figma and code, but it does not say when a narrower tool such as jev_push_screens would be preferable. This is implied usage rather than explicit routing.

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