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

Annotations already provide mutating/idempotent/non-destructive flags, and the description adds genuinely useful behavioral context beyond them: the action records a persistent per-movie anchor, computes scale+offset, and warns about a subtle failure mode where passing screen-adjusted time silently shifts the anchor by the existing offset. No contradiction with annotations.

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

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

Four sentences with no filler: the purpose is front-loaded, the recommended parameter is given immediately, and the warning is dense but essential. 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 4-parameter mutation tool with no output schema, the description covers the core workflow, the one serious time-source footgun, and the required-parameter recommendation. The only notable gap is store_id, which has a default and may be session-derived, so it is unlikely to block a basic 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 carries full parameter-documentation burden. It explicitly explains spoken_text and subtitle_time, and 'pause position' maps to actual_time, but store_id is never mentioned, and actual_time is only implied rather than named. This is a meaningful partial compensation, not complete.

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 first sentence states a specific action and resource: it records a per-movie sync anchor from the current dialogue/pause position and calculates a two-point scale+offset. This clearly differentiates calibrate_sync from sibling tools such as start_overlay or translate_subtitle, so the purpose 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?

The description gives concrete guidance for the recommended input path ('권장 경로는 spoken_text') and a clear exclusion: subtitle_time must be the raw subtitle-file time, not the screen time after an offset is applied, otherwise the anchor drifts. It does not name a sibling alternative, but no sibling covers sync calibration, so this is sufficient context.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds platform scope (macOS CoreText) and the language-support check, but does not disclose the exact return shape or edge-case behavior.

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

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

One concise, front-loaded sentence that names the action, scope, and purpose without filler. Every element 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, read-only, one-parameter enumeration tool with strong annotations, the description is largely sufficient: it states the platform, what is listed, and the per-language check. It stops just short of describing the exact result shape, which is a minor gap given there is no output schema.

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 single `language` parameter has no schema description (0% coverage). The tool description clarifies that language is the target language for glyph support, but it does not specify accepted formats or values beyond the default 'ko', so it only partially compensates 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 description states a concrete action ('enumerate') and a specific resource ('macOS CoreText installed fonts'), then adds a distinct purpose: checking sample glyph support for a target language. This clearly separates it from subtitle/overlay sibling tools like list_subtitles and status.

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 explicit when-to-use or alternative tool is given. The description implies it is relevant when font/glyph support for a language matters, e.g., before configuring subtitle style, but leaves that inference to the agent.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering safety. The description adds useful context about file types and parsing info, but does not disclose return format or pagination behavior, which would add value beyond annotations.

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

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

Single sentence, highly concise, front-loads the key facts (list, file types, parsing info). No filler or redundant 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 zero-parameter read-only list tool, this is complete. Annotations cover safety, description states exactly what is listed, and no output schema means the agent only needs to know the tool's purpose.

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 are zero parameters, so schema coverage is trivially 100%. The description correctly implies no inputs are needed. Baseline 4 is appropriate since no parameter explanation is necessary.

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

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

Description clearly states the action (list) and the specific resource (SRT/SMI/VTT files and parsing info in the tvsub subtitles/ library). It is easily distinguishable from sibling tools like load_subtitle or start_overlay.

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 use this tool versus alternatives. While the name and description make its purpose obvious, it does not explicitly mention exclusions or context for choosing it over siblings.

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

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

Annotations already convey idempotency and destructiveness, and the description adds one useful behavioral detail: existing sync anchors are preserved by default. This hints that a reset option can change that behavior, but it does not explain what actually gets destroyed or when, so the disclosure is partial.

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 short sentences with the purpose front-loaded and no filler. Every sentence earns its place, making it appropriately concise for a lightweight tool definition.

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 three parameters, zero schema descriptions, and no output schema, this description is too sparse for an agent to invoke the tool correctly. It omits how store_id is used, what format subtitle expects, what reset_anchors resets, and what the result or side effects beyond default anchor preservation are.

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 the three parameters, but it never names store_id, subtitle, or reset_anchors. It only indirectly hints at reset_anchors through 'sync anchors are preserved by default', and the tool name/description minimally clarifies the subtitle 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?

The description states a specific verb ('selects') and resource ('subtitle') with the context 'for content', making the tool's core function clear. It is implicitly distinct from siblings like list_subtitles and translate_subtitle, though it never names an 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?

No guidance is given about when to use this tool versus siblings such as list_subtitles, translate_subtitle, or calibrate_sync. The phrase 'for content' provides weak context, but there are no prerequisites, exclusions, or alternative-routing instructions.

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

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

Annotations already convey idempotency, non-destructiveness, and read-write behavior. The description adds the exact state transition to user_reviewed, which is helpful, but it does not disclose any additional side effects, error behavior, or requirements beyond the annotations.

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

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

The description is a single, focused sentence with no filler. It front-loads the action and target, making it easy to scan and understand.

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?

While the operation itself is simple and idempotent, the description omits the meaning of the sole required parameter and gives no usage context beyond the state transition. With no output schema and 0% parameter coverage, this leaves an agent guessing about how to correctly supply 'subtitle'.

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, 'subtitle', has 0% schema description coverage, and the description does not explain whether it is an ID, path, SRT content, or something else. The phrase 'translated SRT' gives a weak hint but does not compensate for the missing parameter documentation.

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 ('갱신합니다' / updates) with a clear resource ('번역 SRT의 provenance 상태') and an explicit target state ('user_reviewed'). This clearly differentiates it from siblings like translate_subtitle or set_glossary.

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 after a translation has been reviewed is implied by 'user_reviewed', but the description never explicitly states when to use this tool versus alternatives, nor does it mention prerequisites. There is no exclusion guidance for other provenance-related 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?

The annotations already declare readOnlyHint, idempotentHint, and destructiveHint, covering the safety profile. The description adds valuable context beyond that: it discloses the use of MediaRemote/JXA and TV.app AppleScript and the cross-validation approach, which reveals dependencies and a behavioral trait not present in the annotations.

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

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

The description is a single, dense sentence with no filler. It front-loads the queried fields and then states the verification method. Every part earns its place, making it highly efficient for an agent 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?

With no output schema, the description carries the burden of explaining what the tool returns. It explicitly lists title, content ID, position, and playback state, which is the core of what an agent needs. It stops short of detailing return shape or edge-case behavior (e.g., no active playback), so it is complete but not exhaustive.

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

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

The input schema has zero parameters, so the schema carries no burden. The description doesn't need to explain parameter meanings, and it doesn't introduce any confusion. The baseline of 4 for zero-parameter tools 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 uses a specific verb '조회합니다' (queries) and clearly identifies the resource: current title, content ID, position, and playback state. It distinguishes itself from sibling tools by naming exact data fields and the cross-validation mechanism, leaving no ambiguity about what this tool reads.

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 makes the usage context clear: a read-only query for current playback information. It does not explicitly name alternatives or exclusion conditions, but the scope is specific enough that an agent can correctly infer when to use it, especially given the sibling list.

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

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

Annotations already convey readOnlyHint=false, destructiveHint=true, and idempotentHint=true; the description adds the file-location behavior (next to the subtitle) and that it creates or modifies the file. However, it does not disclose whether existing files are overwritten or any other side effects, though the annotations reduce the burden.

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 sentence with no filler. It efficiently communicates the core action, target file, and placement in one line.

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 two required parameters, no output schema, and zero schema descriptions, this description leaves major gaps: what exactly 'subtitle' refers to, what shape 'glossary' should take, and how existing files are handled. The description covers the what but not the how or when.

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 does not explain the 'subtitle' string or the 'glossary' object. The phrase 'next to the subtitle' implicitly hints that 'subtitle' identifies the target location, but this is too weak to meaningfully compensate for the lack of schema descriptions.

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

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

The description states a specific verb ('create/modify') and a specific resource ('<work>.glossary.json' placed next to the work's subtitle). This clearly distinguishes the tool from siblings like set_style or translate_subtitle.

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 no guidance on when to use this tool versus alternatives, nor does it mention any exclusions or prerequisites. Usage context must be inferred entirely from the tool name and the file-placement detail.

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 provides valuable behavioral context beyond annotations: it explains the unit conventions for outline_width and bottom_margin, warns about usability issues when outline_width exceeds 10, and mentions that changes are saved and immediately reflected. This is more than the idempotentHint/destructiveHint annotations already convey.

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 overall purpose in the first sentence, followed by targeted clarifications for the two trickiest parameters. Every sentence adds value and there is 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?

Given 9 parameters and no output schema, the description covers the most critical parameter quirks but misses some information like color format or how language is used. It is adequate for basic use but not fully comprehensive for all parameters.

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 thoroughly explains outline_width and bottom_margin, which are non-obvious, but it leaves other parameters (color, font_size, max_lines, font_family, background_alpha, etc.) without explicit semantic detail. The names give some hints, but the description does not fully cover all 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 states clearly that the tool sets and saves overlay style (font, size, color, outline, bottom position) and immediately applies it to the running overlay. It uses specific verbs and a clear resource, and it is easily distinguished from sibling tools like load_subtitle or start_overlay.

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 usage whenever you need to change overlay style, but it does not explicitly state when to use this tool versus alternatives. There are no competitor tools for style setting among siblings, but the description also does not mention prerequisites 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?

Annotations indicate idempotentHint=true and destructiveHint=false, and the description does not contradict them. It adds useful detail about bottom_margin being relative to the TV video window height with a fallback to settings when the window is not found, but it does not explain overlay lifecycle or other 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?

The description is two concise sentences with no filler. The primary purpose is stated first, and the most ambiguous parameter is clarified immediately after.

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 7 parameters, no schema descriptions, no output schema, and a large sibling set, the description is incomplete. It addresses only one parameter's semantics and offers no guidance on overlay behavior, return values, or when to invoke it over related 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 the 7 parameters. Only bottom_margin receives any semantic explanation; color, store_id, subtitle, font_size, font_family, and outline_width are left to inference from their names.

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 starts a tvsub NSPanel overlay with a selected subtitle and style, using a specific verb and resource. It is distinguishable from stop_overlay by its action, but it does not explicitly differentiate itself from related tools like load_subtitle or set_style.

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 explicit guidance on when to use start_overlay versus alternatives such as load_subtitle, set_style, or stop_overlay. It implies its use by naming what it does, but it does not state conditions, prerequisites, 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?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds no extra behavioral context beyond listing the domains of state, but it does not contradict the annotations. With annotations present, a score of 3 is appropriate for not adding further nuance.

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 with the core action front-loaded ('한 번에 요약합니다'). It lists eight distinct domains, which makes it slightly dense, but every item is meaningful and the sentence structure is efficient.

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

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

Given zero parameters, rich annotations, and the tool's simple read-only purpose, the description covers the essential scope well. It lists all state domains comprehensively, though it does not specify the return format or what happens when no state is active; these are minor gaps for this low-complexity 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 the baseline is 4. The description correctly avoids any parameter-related details, as there is nothing to explain. No schema-based ambiguity exists.

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 ('요약합니다' — summarizes) and names the exact resources covered: overlays, playback items, subtitles, sync calibration, styles, and window position tracking contract. This clearly distinguishes it from sibling tools that each handle a single aspect (e.g., now_playing, list_subtitles) by signaling it is a comprehensive state summary.

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 phrase '한 번에 요약합니다' (summarizes at once) implies the tool is for getting an overall status snapshot, but it does not explicitly state when to prefer this over siblings or when not to use it. No alternatives or exclusions are mentioned, leaving usage largely 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?

The annotations already declare idempotentHint=true and destructiveHint=false, which cover safety. The description adds the scoping detail that only overlays started by this server are affected, but it provides no additional behavior like error handling, permissions, or side-effects, which is acceptable given the hints.

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 a single, concise sentence in Korean that directly states the action and scope. No filler or redundant information; it earns every word.

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

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

Given zero parameters, no output schema, and clear annotations, the description is nearly complete. It specifies the exact scope, and the only missing piece is edge case behavior (e.g., what happens if no overlay is running), but that is minor for such a simple 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 the schema needs no explanation. The description fully covers the absence by not needing any parameter context. Baseline 4 is appropriate because no parameter information is required or expected.

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 'terminates' (정상 종료) and a clear resource: the tvsub overlay process started by this MCP server. It explicitly distinguishes it from siblings like start_overlay, making its purpose 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?

The description gives no guidance on when to use this tool versus alternatives. It does not mention prerequisites, such as needing a running overlay, nor does it suggest any alternative or when not to use it. This is a notable gap for a tool that naturally pairs with start_overlay.

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

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

Annotations are sparse (readOnlyHint=false, destructiveHint=false, idempotentHint=false), and the description adds genuine context by disclosing that timestamp/cue-count validation, caching, and provenance are applied regardless of backend. This goes beyond what the annotations declare and does not contradict them, though it omits auth requirements and rate-limit behavior.

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

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

Two sentences with no filler: the core purpose and backend options lead, and the common applied features follow in a dense second sentence. The structure is front-loaded and efficient, though the Korean phrasing may present minor accessibility friction for some agents.

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 an 11-parameter mutation tool with no output schema and zero parameter coverage, this description is insufficient — an agent cannot determine the meaning of time_start/time_end, line_start/line_end, batch_size, glossary, or what the tool returns on success or failure. The description covers only purpose and backend, leaving the invocation contract largely undocumented.

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 11 parameters, so the description carries the full burden but only explains the backend parameter values (auto/api/claude/codex). The other ten parameters (force, dry_run, glossary, line_end, time_end, batch_size, line_start, time_start, target_language, subtitle) are left with only their bare schema 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 states a clear verb ('번역합니다' / translates) and resource (자막 / subtitles), and adds specificity by naming the three backend options (Anthropic API, Claude Code CLI, Codex CLI). Siblings like load_subtitle, list_subtitles, and status perform clearly different operations, so an agent can infer the purpose, though the description never explicitly differentiates itself from related 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?

No guidance is given on when to use this tool versus alternatives — there are no conditions, exclusions, or routing to sibling tools. The only usage hint is the backend value set (auto/api/claude/codex), which tells the agent which values are available but not which scenario calls for the tool.

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