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

With no annotations, the description carries the full behavioral burden for a mutation tool and delivers little. It does not state that a new mask is appended, how the layer is resolved, whether the operation is undoable, or what happens on invalid shape/bounds combinations; the listed attributes (mode, feather, opacity) merely repeat schema fields.

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 well-front-loaded sentence with the action first and shape types as a parenthetical. It is efficient, though the shape enumeration slightly duplicates the shapeType enum already in the schema.

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

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

For a 15-parameter mutation tool with no annotations and no output schema, the description is thin. It omits the critical targeting question of how layerName/layerIndex/compName combine and how shapeType gates which of bounds, vertices, and tangents are actually used.

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 the schema already documents all 15 parameters including defaults and enums. The description's mention of mode, feather, and opacity adds nothing beyond the schema, so the baseline 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+resource ('Add a new mask to a layer') and enumerates the supported shape geometries. It does not explicitly differentiate itself from the sibling setLayerMask, so an agent must infer the add-vs-modify distinction, but the core 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?

No when-to-use guidance is given. The presence of a sibling setLayerMask makes the omission meaningful: nothing tells the agent when to create a mask versus update an existing one, nor what prerequisites (comp/layer targeting) must hold.

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

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

With no annotations, the description carries the full behavioral burden and mostly does not. It never says the tool mutates an existing text layer, whether it adds a second animator alongside existing ones, whether the operation is undoable, or what happens if the target layer/composition is missing.

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

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

A single front-loaded sentence with the core verb first and details following. The parenthetical preset list duplicates the schema enum, but it is compact and aids selection rather than bloating the text.

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 10 parameters, nested rangeSelector/wigglySelector objects, and no output schema, the description covers only the preset dimension. It omits how presets interact with custom properties and selector configuration, leaving real gaps for a tool of this complexity.

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% with 10 well-described parameters, so the baseline is 3. The description only restates the preset enum and the "per-character 3D" note for 3d_flip_chars, adding essentially no semantics beyond the schema.

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 ("Add an AE text animator") and enumerates the two capability modes: full selector/property control or predefined presets. No sibling tool touches text animators, so the agent can place it immediately.

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 "or custom" hints that presets and manual properties are alternative paths, but there is no statement of when to pick one over the other, no prerequisite that a text layer must exist, and no guidance on combining rangeSelector vs wigglySelector. The agent must infer the usage model.

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

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

No annotations are provided, so the description carries the full behavioral burden. For a mutation tool it omits whether existing keyframes/properties are overwritten or merged, whether it is reversible, whether it requires network/AI access and is non-deterministic, and what the user is charged in latency. It only notes the optional screenshot input.

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

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

A single dense sentence that front-loads the verb, resource, and mechanism, with the capability list and the screenshot option trailing. Efficient with no filler, though the parenthetical list makes it slightly overloaded.

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 a 5-parameter mutation tool with no annotations and no output schema, the description covers purpose and capability scope but leaves key behavioral questions unanswered (destructiveness, determinism, AI dependency). It is adequate but not complete for the complexity involved.

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 the schema already documents all five parameters (prompt, compName, layerName, layerIndex, attachScreenshot). The description adds only the 'optional visual screenshot input' hint, which duplicates attachScreenshot rather than adding new meaning, so baseline 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+resource: 'Instruct AI to modify a specific layer in After Effects using natural language prompt', and enumerates the capability scope (transforms, keyframes, effects, masks, expressions). This clearly sets it apart from the granular siblings like applyEffect or setLayerProperties, 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?

The natural-language framing implies when to reach for this tool versus the surgical siblings, but the description never states that explicitly nor gives any when-not guidance or prerequisites (e.g. does it require a layer to be selected or an AI backend?). Usage is implied rather than directed.

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 add genuine context: the models are bundled (MMS-Align, CTC ONNX, Silero VAD v6, Viterbi trellis) so no external setup is implied, and it discloses the return payload (word/line timestamps, confidence, LRC drift corrections, drum-beat offsets). It says nothing about runtime cost, accuracy limits, or failure behavior (e.g., missing LRC, speechless audio) for what is presumably a heavy inference job.

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 sentence that front-loads the action and file target before listing outputs, so an agent gets the gist immediately. The parenthetical model stack ('Neural CTC ONNX + Silero VAD v6 + Viterbi CTC-Segmentation trellis') is largely decorative and could be trimmed without losing meaning.

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 7-parameter inference tool with no annotations and no output schema, the description covers purpose and return contents but leaves gaps: how its output feeds siblings like createAlignedLyricLayers, what happens when no lyrics source is found, and expected cost/duration. Adequate to start, incomplete for confident 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 100%, so the schema already documents all 7 parameters and a baseline of 3 applies. The description adds only indirect hints — snapWordsToBeats is reflected in the 'nearest drum beat offsets' output mention and LRC handling in 'LRC drift corrections' — with no extra format or interaction details.

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 ('Perform frame-accurate forced alignment of lyrics/subtitles against an audio file') and names the concrete pipeline used, which is unmistakable against siblings like applyBeatMarkersToComp or createAlignedLyricLayers. It never explicitly says how it differs from those neighbors, so an agent must infer the boundary itself.

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

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

There is no when-to-use / when-not-to-use guidance and no routing to alternatives, despite several plausible siblings (analyzeAudioRhythm, analyzeMusicEmotionWithMusiCNN, createAlignedLyricLayers) that an agent could confuse it with. Prerequisites such as needing an existing LRC file or the audio containing vocals are left entirely implicit.

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 zero annotations the description must carry the load, and it does disclose what the operation yields in concrete terms (specific frequency bands, downbeat meter, section taxonomy), which is real behavioral detail rather than a restatement of the name. It omits notable traits such as expected runtime on long files, whether analysis is deterministic, or behavior on files with no detectable beat, so it is 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?

One front-loaded sentence with a tightly packed enumeration where each item (bands, sections, energy envelope) carries information. The parenthetical Hz ranges and section names make it long but not padded; minor cost is that a reader must scan the whole list to find the input expectation.

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 usefully enumerates the return payload (BPM, beat grid, downbeats, onsets, energy, sections), and all six inputs are documented in the schema. It is sufficient to call correctly; only latency and edge-case behavior are unaddressed.

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

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

Schema description coverage is 100%, with minBpm/maxBpm defaults, sensitivity range, and time-window semantics all documented in the schema. The description adds nothing about these knobs (e.g. when to widen the BPM bounds or lower sensitivity), so the baseline 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 ('Extract') plus the exact resources produced: BPM, beat grid, 4/4 downbeats, sub-band drum onsets with Hz ranges, energy envelope, and named structural sections. This is unmistakably different from the sibling audio tool analyzeMusicEmotionWithMusiCNN (emotion) and from applyBeatMarkersToComp (which consumes markers rather than extracting them), so an agent can route without opening the schema.

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 trailing clause 'to help align VFX, camera cuts, and text animations to music' implies the downstream use case, which is useful context. However, it never states when to pick this over the sibling analyzeMusicEmotionWithMusiCNN or applyBeatMarkersToComp, and gives no prerequisites or exclusions, leaving the choice to inference.

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

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

With no annotations, the description carries the full behavioral burden. It usefully discloses the bundled models, optional lyric fusion, and the kinds of outputs including per-window camera and character choreography, but it omits runtime expectations, file limitations, side effects, whether files are written, and permission requirements.

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 purpose is front-loaded and the output list is relevant, so most content earns its place. However, it is a single dense run-on sentence, and the model citation parenthetical adds detail that is not essential for tool selection.

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?

There is no output schema, so the description must explain return values; it does so by enumerating the tag set, trajectory data, turning points, and choreography outputs. Parameters are fully documented in the schema, but operational context for this complex analysis tool remains thin.

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 every parameter already has documented meaning. The description adds no additional parameter semantics such as value ranges, default behavior nuances, or interactions beyond what the schema states.

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

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

States a specific verb and resource: analyze an audio file for music emotion using named bundled models. The output scope (50 tags, valence-arousal-tension trajectories, turning points, character choreography) clearly separates it from rhythm-focused siblings like analyzeAudioRhythm.

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 when-to-use or when-not-to-use guidance, and no named alternative is compared. The only routing hint is that lyricsText/lrcFilePath can fuse lyric affect, but an agent is not told when to choose this tool over analyzeAudioRhythm, alignLyricsWithMMS, or createAlignedLyricLayers.

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

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

With no annotations, the description carries the full burden. It does disclose the concrete side effect and its artifacts (labeled Downbeats, Beats, Kick, Snare, Major Impacts) and where they land (comp timeline vs. layer), but it never says what happens to pre-existing markers, whether the operation is undoable, or that audio analysis is potentially slow/long-running.

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: verb first, parenthetical label list second, target third. No filler or repetition; it could be marginally tighter by folding the label list into the marker-mode phrase, but it is well structured.

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 7-parameter mutation tool with full schema coverage and no output schema, the definition covers purpose and result artifacts adequately. What is missing — return value/analysis latency, failure on unreadable audio, and interaction with existing markers — is moderate rather than fatal, but with zero annotations the description should have picked up more of that slack.

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 the schema already documents all seven parameters including the `markerMode` enum. The description adds only light mapping between the listed marker labels and the marker-mode choices, and says nothing about the semantics of `startTime`/`endTime` or `clearExistingMarkers` beyond what the schema states. Baseline 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?

States a specific verb chain ("Analyze audio beats & drum hits and automatically inject labeled markers") plus the concrete resource (markers in an After Effects composition or target layer). An agent can tell what it does, though it never names the sibling `analyzeAudioRhythm`, so the boundary between analysis-only and analysis-plus-marker-injection is left to inference.

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

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

Usage is implied by the effect ("inject markers into a composition or target layer") but there are no explicit when-to-use/when-not statements and no prerequisites such as needing an open project or a valid audio file. The presence of the closely related `analyzeAudioRhythm` sibling makes the absence of a routing sentence a real gap.

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 a meaningful behavioral trait: automatic keyframing and easing are applied, which is not obvious from the name. However, it says nothing about required setup (camera layer, active comp), whether it mutates existing keyframes, or what it returns.

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

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

A single front-loaded sentence that efficiently conveys purpose, mechanism, and full move-type vocabulary. No filler.

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

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

For a 13-parameter tool with no annotations and no output schema, the description is adequate on purpose and mechanism, but omits prerequisites, side effects, and return behavior. It is minimally viable but has clear gaps an agent would need to infer elsewhere.

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 name '运镜' and parenthetical Chinese aliases map to moveType enum values, but the schema already documents every parameter at 100% coverage, including enum values and defaults. The description adds no syntax, format, or semantic detail beyond what the schema provides, 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 ('Execute') and resource ('cinematic camera movements') and enumerates all 12 move types, which makes the tool's scope unambiguous. It doesn't differentiate itself from siblings like setCameraProperties or createCameraRig, so it falls short of a 5.

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

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

No when-to-use guidance, no prerequisites (e.g., must a camera exist first?), and no mention of alternatives to this tool. The enumeration of move types implies the use case but provides no routing logic.

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 burden of behavioral disclosure. It does not state whether the effect is appended or replaces existing effects, what happens if the effect or layer is not found, or whether a target layer must be selected first — gaps that matter for a mutation tool.

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

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

A single efficient sentence that front-loads the action and the resource. Nothing is wasted, though the brevity comes at the cost of the missing behavioral and targeting detail noted elsewhere.

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

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

For a mutation tool with five parameters, a nested properties object, no annotations, and no output schema, the description is thin. It omits how to disambiguate the target layer (compName+layerName vs layerIndex), how the initial properties object behaves, and any error/return 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 all five parameters (including the nested properties object) are already documented in the schema. The description only restates that the effect can be given as display name or matchName, adding no meaning beyond the schema's own example list, so the baseline 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+resource ("Apply an effect or third-party plugin to a layer") and clarifies that the effect is identified by display name or matchName. This makes it easily distinguishable from siblings like setEffectProperties, removeEffect, and reorderEffect, though it never names those siblings explicitly.

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

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

The description implies usage (attach an effect to a layer) and gives the naming convention for effectName, but offers no when-to-use vs when-not guidance and no prerequisites. It does not explain how to choose the target layer among compName/layerName/layerIndex, which an agent must infer.

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 discloses one meaningful trait — all updates happen in a single transaction — but says nothing about rollback-on-failure behavior, partial failure handling, or required permissions, which is the critical unknown for a batch mutation tool.

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

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

A single front-loaded sentence with no redundant or filler content. Every clause (verb, resource, batching, transaction) 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?

The schema fully documents inputs and there is no output schema to explain, but for a destructive batch mutation with zero annotations the description should state failure/rollback semantics and the return shape. Those gaps leave the agent guessing about a transactional operation's edge cases.

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%, with each field and the nested properties object documented, so the baseline is 3. The description adds no parameter-level meaning beyond confirming batch semantics.

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 ('Apply property updates'), resource ('layers'), and scope ('multiple layers simultaneously in a single transaction'). It implicitly distinguishes itself from the singular setLayerProperties sibling via 'multiple layers', but 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 on when to prefer this over setLayerProperties, or when batching is required. 'In a single transaction' hints at atomicity-driven use cases but the agent must infer that.

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 must fully disclose behavior. It says the tool deletes backup/duplicate files (destructive), but it does not state whether deletion is permanent, whether a confirmation prompt exists, what permissions are needed, or where the default scan occurs. This is a significant gap for a destructive 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?

A single, front-loaded sentence that states the scan target, cleanup action, and user-visible benefit without any 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?

With no annotations, no output schema, and a destructive operation, the description should explain irreversibility, default behavior, and what 'scan' reports. It only provides the high-level purpose, leaving essential behavioral details missing.

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 optional parameter (targetDir) with 100% schema description coverage. The description does not mention the parameter at all, but the schema already explains it clearly, so baseline 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 (scan and clean up) and resource (backup/duplicate jsx files in After Effects ScriptUI Panels), plus the user-facing consequence (Window menu clutter). No sibling tool performs this function, but the description does not explicitly distinguish it from siblings, so a 4 is appropriate.

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

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

The description implies when to use it—when backup/duplicate jsx files cause clutter in the Window menu—but does not explicitly state when to use it versus alternatives or mention any prerequisites or exclusions. Usage is inferable but not explicit.

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

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

No annotations are provided, so the description carries the full behavioral burden. 'Modify' implies a mutation, but it does not state whether partial updates are merged or reset, whether changes persist across sessions or require a restart, or whether any permission is needed. Only the schema's default values hint at 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?

A single compact sentence that front-loads the verb and resource and then lists the configurable knobs. No filler, though the parenthetical gloss on autoSave is the only explanatory 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 an all-optional, six-parameter mutation tool with no annotations and no output schema, the description identifies what can be changed but omits persistence/restart behavior and what the call returns. Adequate minimum viability given the schema documents every parameter, but with a real gap around effect timing.

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 of the six properties has its own description with defaults and enum meaning, so the schema already does the heavy lifting. The description only restates a subset of parameter names (and abbreviates 'history limit' / 'timeouts' rather than matching maxHistory / timeoutMs), adding no semantics beyond the schema. Baseline 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 ('Modify') and resource ('MCP settings') and enumerates the affected settings (autoSave, autoRecordHistory, saveMode, history limit, timeouts), which lets an agent distinguish it from the read-only sibling getSettings. It stops short of naming that sibling explicitly, 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?

The description never says when to use this tool versus getSettings (read the settings) or when settings should be changed. There are no prerequisites, no note about when changes take effect, and no exclusions.

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

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

No annotations are provided, so the description carries the full behavioral burden. It hints that 3D transforms are 'pre-configured' but does not disclose defaults, which composition the layer is added to, whether a comp must be active, or what happens on size/color conflicts. For a 12-parameter creation tool with zero annotation coverage, this is a substantial 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 efficient sentence with no wasted words, front-loading the verb and resource. It is appropriately sized, though the brevity comes at the cost of the missing behavioral and usage detail noted elsewhere.

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

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

For a 12-parameter mutation tool with no annotations and no output schema, the description is too thin. It omits the target composition context, defaults for 3D transforms, and how it relates to the near-identical sibling creators, leaving an agent without enough to call it confidently.

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 the schema already documents every parameter including the layerType enum and conditional usage of text/color. The description's type list merely restates the enum, adding no syntax or interaction detail beyond the structured fields. Baseline 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 (Create) and resource (3D layer), and enumerates the creatable types (solid, text, null, shape). However, it does not distinguish itself from overlapping siblings like createSolidLayer, createTextLayer, and createNullObject, which appear to create the same layer types without the 3D transform prefix.

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

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

There is no guidance on when to use this tool versus the sibling creators (createTextLayer, createSolidLayer, createNullObject) or versus set3DLayerTransform. The agent is left to infer that this is the 3D-enabled variant, but nothing states prerequisites or the conditions that select 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 full burden. It usefully discloses the 'unclipped 3840x3840' output size, the automatic 3D child scale-reset, and the parented inner world for teardrop_portal, which are genuine behavioral traits. However it omits whether the Saber plugin must be installed, which composition layers are written to, and what the tool returns or whether it is undoable.

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 front-loaded sentence with no filler, but it is dense and stuffs an enum list into a description where the schema already defines the same five values, so a portion does not earn its place. The nested parentheses make it harder to parse at a glance.

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 12-parameter creation tool with no annotations and no output schema, the description covers purpose and some behavior but leaves gaps: no return value, no indication of which comp the layers land in beyond the compName parameter default, and no plugin-dependency note. It is adequate but incomplete for the tool's complexity.

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 the schema already documents all 12 parameters, including units and defaults. The description adds only marginal meaning, mainly that the inner-world flag applies only to teardrop_portal and that endPosition supports a falling teardrop. Baseline 3 is appropriate when the schema does the heavy lifting.

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?

Clearly states a specific verb+resource: creates a 3D Video Copilot Saber energy symbol or portal, and enumerates the preset shapes. No sibling tool overlaps with this purpose, so differentiation is implicit rather than stated, which keeps it just below a 5.

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

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

There is no guidance on when to use this versus alternatives (e.g. createSolidLayer or applyEffect), no prerequisites such as requiring the Saber plugin installed, and no exclusions. The agent must infer usage entirely from the name and description.

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 burden. It establishes that this is a mutating, layer-creating operation inside a live comp, but says nothing about whether existing aligned layers are destroyed or duplicated on re-align, whether the run requires the bridge/plugin to be live, expected runtime for MMS alignment, or whether the result is undoable.

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

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

A single dense sentence with the action and outcome front-loaded and no filler. It is packed with domain jargon (MMS-Align, CTC-Segmentation) that may cost some readers, but every clause 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 ten-parameter, annotation-free mutation tool with no output schema, the description establishes the pipeline and output artifact but omits what is returned (layer names, count, timing data), what happens when neither lyricsText nor lrcFilePath is supplied, and what state the comp is left in. Adequate as an introduction, incomplete as the sole documentation.

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%, so all ten parameters are already documented, which sets the baseline at 3. The description only indirectly touches parameters by mentioning audio, lyrics, 3D layers, and beat-locked timing, without adding syntax, format, or precedence rules beyond the schema.

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 pipeline (MMS-Align / CTC-Segmentation) and a concrete output artifact (3D kinetic typography text layers in the After Effects composition) with beat-locked pop/fade animations. That is far more specific than the name alone. It stops short of a 5 because it never distinguishes itself from close siblings like alignLyricsWithMMS or applyBeatMarkersToComp, which sound like subsets of this same pipeline.

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 when-to-use statement and no exclusion or routing to alternatives, even though alignLyricsWithMMS and applyBeatMarkersToComp cover overlapping ground. The parenthetical '(or re-align)' hints that the tool also re-processes already-created layers, but the agent must infer that the tool creates layers when none exist and overwrites when they do.

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

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

With no annotations, the description carries the full burden and does disclose genuine behavioral traits: the spine is trigonometrically locked so the body never separates when leaning, paths are boolean-unioned, and the glow is bounds-grown to avoid clipping. What it omits is equally important for a creation tool — whether a new composition is made or layers are added to the existing one, what side effects occur, and any permission/plugin requirements.

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 sentence with the verb front-loaded and no filler, but it is overloaded with parenthetical jargon and reads as a feature dump rather than a scannable definition. Splitting the core action from the rendering guarantees would improve parseability without adding length.

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 13-parameter creation tool with full schema coverage and no output schema, the description is close to sufficient — it conveys what is built and key visual invariants. The remaining gap is what the caller gets back (a comp, a set of layers, a precomp) and whether the operation requires an open composition, which no structured field covers.

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%, so the schema already documents all 13 parameters, including the boy/girl anatomy and the enum values — the description largely restates these. Its only real added value is the '7-joint' framing, which implicitly maps to the seven rotation fields in poseKeyframes (arms, legs, head, torso, hair/tie sway).

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?

Opens with a specific verb+resource: 'Create a 3D 7-joint articulated character silhouette rig', which an agent can immediately map to a layer-creation action and distinguish from siblings like create3DSaberSymbolOrPortal or createTextLayer. The remainder is a dense feature list (Merge Paths Type 2, Grow Bounds + Glow2) that adds specificity but obscures the core statement.

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

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

There is no statement of when to use this tool, when not to, or what prerequisites apply (3D renderer enabled, Glow2/Merge Paths plugin availability, active composition required). Nor does it explain when to pick posePreset versus supplying custom poseKeyframes, even though both are exposed.

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 full burden of behavioral disclosure. It does not mention side effects, permissions required, whether it modifies the active composition, or what it returns. It only restates features available via the schema.

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 efficiently names the action and resource before listing capabilities. Every word earns its place with 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 20 parameters, no annotations, and no output schema, the description is thin. It covers the core purpose but omits behavioral context such as target composition, side effects, and return value. The rich schema partially compensates for parameter details, leaving the description adequate but with clear gaps.

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

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

Schema description coverage is 100%, so the schema fully documents all 20 parameters. The description adds only a high-level summary of a few features (focal presets, depth of field, aperture, camera rig), providing no syntax or default details beyond what the schema already provides.

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 a specific verb ('Create') and resource ('1-node or 2-node 3D camera layer'), and lists key features. It distinguishes implicitly from siblings like setCameraProperties by being a creation tool, but does not explicitly name alternatives.

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 guidance on when to use this tool versus alternatives such as setCameraProperties or createCameraRig. The purpose implies usage but provides no when/when-not context or exclusions.

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

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

No annotations are provided, so the description carries the full burden. It does disclose the compound structure it builds (two nulls plus a parented camera), which is genuine behavioral context. However, it omits mutation side-effects, whether it needs an active composition, undo behavior, and what it returns.

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

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

A single front-loaded sentence with no wasted clauses; the core action and its components come first. Minor marketing filler ('professional industry-standard', 'effortless') slightly dilutes it but does not hurt scanability.

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

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

For a five-parameter creation tool with no output schema and no annotations, the description explains what is built but says nothing about the return value (e.g. the created rig objects) or the composition prerequisite implied by the compName default. Adequate but with a real gap.

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% across all five parameters, so the schema already documents rigName, compName, distance, cameraName, and targetPosition with defaults. The description adds no parameter-level detail, so the baseline 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?

States a specific verb (Create) and resource (3D Camera Rig), and names the concrete output structure — Target Null, Orbit Null controller, and parented Camera. It implicitly distinguishes from createCamera (single camera) and createNullObject, but never names those siblings, so the differentiation is inferential rather than explicit.

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 mentions the benefit (orbit and gimbal-lock-free animation) but gives no explicit when-to-use guidance and never points to alternatives like createCamera, createNullObject, or applyCameraMove. The agent must infer that this is for rig-based orbit work.

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 disclose behavioral traits, but it only states that a composition is created. It omits key details like whether the project must be open, whether the new composition becomes active, permission requirements, or 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 a single front-loaded sentence with no unnecessary words. It is concise, though its brevity leaves substantial gaps that are not addressed elsewhere.

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

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

For a creation tool with no annotations and no output schema, the description is too sparse. It does not explain the tool's effect on project state, what happens on naming conflicts, or any limitations, leaving the agent to infer important behavior.

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

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

Schema description coverage is 100%, so the schema fully documents all seven parameters including defaults. The description adds no additional parameter semantics, 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 clearly states a specific verb ('Create') and resource ('composition'), making it easy to distinguish from sibling creation tools like createCamera or createTextLayer. However, it does not explicitly differentiate itself from related composition tools (e.g., renameComposition, setCompositionProperties).

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

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

The description offers no guidance on when to use this tool versus alternatives, nor any prerequisites. It implies creation is needed to start a project, but does not state when a new composition is required or what happens if one already exists.

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

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

No annotations are provided, so the description carries the full behavioral burden. It implies a write operation and lists controllable features, but says nothing about side effects, defaults, permission requirements, or what happens when parameters are omitted. What it does say largely restates the schema.

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 names the action and its major controls with no filler. It is efficient, though the parenthetical enum list slightly duplicates the schema's lightType values.

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 12-parameter mutation tool with no annotations and no output schema, the description is adequate but thin: the schema covers defaults and units, yet the description omits behavioral context such as required scoping (compName) and effects of shadow/angle settings.

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 all 12 parameters already document their units and defaults, so the baseline of 3 applies. The description adds no extra parameter meaning beyond naming a subset of the fields (intensity, color, shadows, angle).

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 verb ("Create") and resource ("3D light layer") and enumerates the supported variants (Point, Spot, Parallel, Ambient), which are the same values as the lightType enum. It is clearly distinct from siblings like createCamera, create3DLayer, or createSolidLayer, though it does not explicitly say so.

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

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

There is no statement of when to use this tool versus alternatives, nor any prerequisite information (for example, whether a composition name must be supplied or which light type suits which situation). The agent must infer everything from the schema.

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

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

No annotations are provided, so the description carries the full behavioral burden. It does not state which composition the null lands in, what happens when compName is omitted, whether the new layer becomes selected, or whether it is reversible — significant gaps for a mutating creation 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?

A single well-formed sentence that front-loads the verb and resource and uses the trailing clause to convey purpose. Nothing is wasted, though it stops short of the compactness-plus-routing of a 5.

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-required-param creation tool with full schema coverage and no output schema, the essentials are covered. It still omits default-comp behavior and post-creation effects that an agent would need when calling it without arguments.

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 the schema already documents name, compName, and duration with their defaults. The description adds no parameter meaning beyond that, so the baseline 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 ('Create') plus a distinct resource ('null object layer') and even names the intent ('rigging, parenting, or animation controls'). The resource is clearly separable from siblings like createCamera, createTextLayer, or createSolidLayer, though it doesn't explicitly contrast itself with them.

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

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

The phrase 'for rigging, parenting, or animation controls' gives implied usage context, so an agent can infer when a null is appropriate. However, there is no explicit when-not-to-use guidance and no routing to alternative layer-creation siblings, leaving selection mostly 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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. 'Create a solid color layer' implies a mutation that adds a new layer to the project, but the description does not mention side effects (e.g., changes to the active composition or selection), permissions required, reversibility, or whether the layer is returned.

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

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

A single, front-loaded sentence with no wasted words. The purpose is stated immediately and clearly, making the description appropriately sized for a straightforward creation tool.

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 that the tool is a mutation with no annotations and no output schema, the description is too sparse. It does not explain what happens upon success (e.g., whether a new layer is selected or returned) or any practical constraints (e.g., whether a composition must be active), leaving the agent uncertain about the full behavior.

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

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

Schema description coverage is 100%, so the input schema already documents all six parameters, including defaults for name, width, height, and duration. The description adds no parameter-level details beyond what the schema provides, which is the baseline for full coverage.

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 (Create), resource (solid color layer), and scope (in the composition). This is clearly distinguishable from siblings like createTextLayer, create3DLayer, createCamera, and createLight, which create different layer types.

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

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

Usage is implied by the purpose: use this tool to add a solid color layer to a composition. However, there is no explicit guidance on when to choose this over alternatives (e.g., create3DLayer, createNullObject) or any 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?

No annotations are provided, so the description carries the full burden. It does not state side effects (does it modify the active composition?), what the tool returns, whether an undo group is created, or permission requirements. For a multi-parameter mutation tool with zero annotation coverage this is a significant gap.

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

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

A single, front-loaded sentence that leads with the action and then compresses the feature set efficiently. It stops just short of ideal because the tail-end enumeration reads like a parameter list rather than decision-relevant information, but there is no wasted prose.

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 24-parameter tool with no annotations and no output schema, the description is thin: it never states what is returned, what happens when compName is omitted, or how effects application interacts with the rest of the parameters. The rich schema compensates for parameter meaning, but the behavioral and return-value gaps keep this at a minimum-viable level.

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

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

Schema coverage is 100% with 24 well-documented parameters, so the schema already does the heavy lifting. The description only groups the parameter categories (font, size, colors, tracking, leading, justification, caps, 3D orientation, effects) without adding format or default detail beyond the schema, matching the baseline-3 case.

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 ('Create a 2D or 3D text layer') and enumerates the typography dimensions it covers. It does not explicitly distinguish itself from the sibling formatTextLayer or create3DLayer, so an agent must infer the difference, but the purpose itself 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?

No when-to-use guidance and no alternatives named, even though siblings like formatTextLayer (modify existing text) and create3DLayer are natural confusions. The agent is left to infer that this is for the initial creation of a text layer rather than editing one.

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 full behavioral burden. It says 'delete' but never states that the operation is destructive/irreversible, whether it can be undone via the project history, or what happens if the named layer does not exist — all important for a mutation tool.

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

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

A single, front-loaded sentence with no wasted words. It is efficient rather than padded, though its brevity is partly under-specification rather than disciplined concision.

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

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

For a destructive mutation tool with zero annotation coverage, no output schema, and identity parameters that are all optional, the description is thin. An agent has no information about failure modes, return value, or how the target layer is resolved.

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 the schema itself documents compName, layerName and layerIndex, which sets the baseline at 3. The description adds nothing about parameter interplay — notably that all three are optional, leaving unclear whether layerIndex takes precedence over layerName or whether compName is required to locate the layer.

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

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

The description gives a specific verb (delete) and resource (layer) with its scope (from the composition), so an agent immediately knows the operation. It does not, however, differentiate itself from adjacent siblings such as duplicateLayer or removeEffect, leaving the agent to infer the boundary from the name alone.

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

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

There is no statement of when to use this tool versus alternatives, no prerequisites, and no mention of the undo/history siblings (rollback, getHistory) that a caller might need. Only the barest implied usage is present.

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 burden. It does not disclose where the duplicate is placed (above/below the original, top of stack), whether a name is auto-generated, whether existing layer references are affected, or what happens when the layer is not found. For a mutating/creating operation with zero annotation coverage, this is a substantial 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 or redundancy. It is efficient, though arguably too terse given the ambiguity around layer identification and duplication placement.

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 annotations, no output schema, and an unaddressed ambiguity about which of layerName/layerIndex identifies the target, the definition leaves the agent unable to call the tool confidently. Placement of the duplicate, return value, and error behavior are all unstated.

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 the baseline is 3. However, the schema descriptions are terse ('Composition name', 'Layer name', 'Layer index'), and the description adds nothing about whether name or index is the identifying input, or how the engine resolves the two given that 0 parameters are required.

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

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

The description states a specific verb and resource: duplicating an existing layer within a composition. It is unambiguous about what the tool does, but gives no differentiation from siblings such as deleteLayer or create3DLayer, so an agent must infer which situations call for duplication rather than creation.

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

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

There is no when-to-use guidance, no mention of prerequisites (e.g., whether an active composition is required), and no pointer to alternatives like createTextLayer or createSolidLayer for producing new layers. The agent gets no help deciding between this tool and its 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?

With no annotations, the description carries the full burden. It does disclose useful behavior: analysis runs on a bundled local ONNX model (no external service), and it lists the full output surface, implying a non-destructive read. However, it omits runtime/latency expectations for a video model, failure modes for unsupported files, and what happens when videoPath has no audio and audioPath is omitted.

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

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

Front-loaded with the action and model, followed by the return payload in one dense sentence with no filler. The parenthetical model expansion is verbose but informative; nothing is repeated from the schema.

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

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

No output schema exists, and the description compensates by enumerating every returned score and diagnostic field, which is exactly what the agent needs to interpret results. Remaining gaps are operational (latency, error cases, audio-absent behavior) rather than about what the tool produces.

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 the schema already documents all four parameters, giving a baseline of 3. The description adds only indirect value by naming the Audio-Visual Beat Sync Score, which hints at audioPath's role, but it does not clarify startTime/endTime behavior (e.g., how segment scores are aggregated over a partial range).

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 ('Score') plus resource ('rendered video') and names the exact model (DOVER-Mobile, ConvNeXtV2-Femto-3D ONNX) and supported formats. It also enumerates the returned score types (Technical, Aesthetic, Fused, Audio-Visual Beat Sync), which makes it unmistakable against siblings like analyzeAudioRhythm or inspectFrameAestheticsAndClipping.

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: 'rendered video' signals it belongs after export/preview rendering. There is no explicit when-to-use / when-not, and no routing against clearly adjacent siblings such as inspectFrameAestheticsAndClipping (single-frame clipping/aesthetics) or analyzeAudioRhythm (beat analysis), leaving the agent to infer which to pick.

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 output format (PNG) and that it returns a base64 preview, which is useful behavioral context, but it omits side-effect details such as whether a file is written to disk by default, where, and any permission requirements 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?

A single front-loaded sentence that names the verb, resource, formats, and return value with no filler. Appropriately sized, though it is terse enough to leave gaps.

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

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

For a five-parameter, file-producing tool with no annotations and no output schema, the description covers purpose and return format but leaves the write side effects, defaults, and sibling routing unaddressed, so it is adequate rather than complete.

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

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

Schema description coverage is 100%, so the schema already documents all five parameters. The description reinforces the frame/time distinction and PNG/base64 output but adds no syntax or default information beyond what the schema provides; baseline 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 (Export) and resource (screenshot/state image of a frame or current time), plus the output format (PNG). It does not differentiate itself from the related sibling exportPreviewVideo, but the purpose itself 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 dual modes 'specific frame or current time' hint at how the tool is used, but there is no explicit when-to-use / when-not guidance and no reference to exportPreviewVideo as the alternative for motion/preview output.

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

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

No annotations are provided, so the description carries the full behavioral burden. It hints at the speed/quality trade-off ('quickly', 'fast low-resolution rendering'), which loosely matches the schema defaults, but it never discloses that this writes a file to outputPath, whether an existing file is overwritten, what dependencies are required (e.g. an open composition), or what is returned.

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 tight sentence with the action front-loaded and no filler. It is appropriately sized for the tool, though it could carry one or two more clauses of genuinely useful behavioral detail without bloat.

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 file-producing export tool with no annotations and no output schema, the description is minimally adequate. The 8 parameters are fully documented in the schema, but the write side effects, overwrite semantics, and required context for a preview render are left unaddressed.

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

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

Schema description coverage is 100%, so the schema already documents all 8 parameters including defaults, enums, and time/frame alternatives. The description only echoes the frame-range concept ('frame A to frame B') and the low-res behavior, adding no syntax or format detail beyond the schema, so the baseline 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 (export), resource (preview video), and scope (specific frame range with fast low-resolution rendering). The 'preview' framing implicitly contrasts with the single-frame exportFrame sibling, but it never names or explicitly differentiates from it, so it stops short of a 5.

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

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

The description gives no when-to-use / when-not-to-use guidance and does not name exportFrame as the alternative for non-video frame exports. Usage can only be inferred from the word 'preview'; no prerequisites or exclusions are stated.

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

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

No annotations exist, so the description carries the full disclosure burden. It does convey that work is queued in an external app and that rendering does not start unless renderImmediately is set, but it omits whether the call blocks, whether it returns a job/render identifier, what happens when AME is unavailable, and whether an existing file at outputPath is overwritten.

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

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

One sentence, front-loaded with the action and target, with zero filler and no 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?

The schema is fully described and there is no output schema to explain, but for a tool that hands work to an external application the description should at least mention the AME dependency and what the agent gets back. Without those, an agent cannot plan around the call's asynchronous nature.

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 each of the three parameters is already documented in the schema, including the default-to-active-comp behavior and the renderImmediately default. The description adds no syntax, format, or constraint detail beyond that, which is the baseline case.

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?

Names a specific verb (send) and resource (composition) plus the destination system (Adobe Media Encoder render queue), and 'high-quality background rendering' implicitly separates it from preview exports. It stops short of naming the sibling it displaces (exportPreviewVideo / exportFrame), so the boundary is inferred rather than stated.

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: 'high-quality' and 'background rendering' suggest a final-quality render rather than a quick preview, which lets an agent guess it should prefer exportPreviewVideo for fast checks. No explicit when-to-use or when-not-to-use guidance, and no prerequisites such as AME needing to be installed or running.

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

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

With no annotations, the description carries the full burden and does disclose the core mutation behavior: inserting ADBE Grow Bounds before ADBE Glow2, expanding small Saber solids, and recentering masks. It still does not state whether the repair is reversible, how existing effects are handled, what happens on failure, or what result is returned.

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 that first states the repair purpose and then explains the mechanism. It is dense with domain jargon but efficient and contains no obvious 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?

The purpose and mechanism are adequately explained, and the five optional parameters are fully covered by the schema. Completeness is limited by the lack of annotations and output schema: the description does not clarify safety, idempotency, failure behavior, or what the agent should expect after the repair.

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 the schema already documents compName, layerName, growPixels, layerIndex, and expandSaberSolidsToSize. The description reinforces the 3840 solid expansion behavior but does not add much parameter-level meaning beyond the schema.

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

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

The description states a specific verb and resource: repairing 3D glow and Saber rectangular boundary clipping across a layer or composition. It is very clear about what the tool does, though it does not explicitly differentiate itself from nearby diagnostic tools such as inspectFrameAestheticsAndClipping.

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

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

Usage is implied by the purpose: use this when glow or Saber bounds clipping needs automatic repair, and choose layer scope via layerName vs composition scope. However, there is no explicit when-to-use guidance, no exclusions, and no named alternative for merely inspecting clipping.

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 must carry the full behavioral burden. It indicates a mutation ('modify') but does not disclose whether changes are reversible, what permissions are needed, how omitted parameters behave, or what happens when the target layer is missing.

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 that begins with the core action and then lists supported attributes. It is dense but avoids filler; the list is long yet every item corresponds to an actual capability.

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 17-parameter mutation tool with no annotations and no output schema, the description is incomplete. It covers the parameter surface broadly but omits usage context, side effects, prerequisites, and return behavior that an agent would need to invoke it safely and correctly.

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

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

Schema description coverage is 100%, so the schema already documents all 17 parameters in detail. The description lists many of the modifiable fields but adds no syntax, format, or behavioral meaning beyond what the schema provides, making the baseline score of 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?

The description gives a specific verb and resource: 'Format an existing text layer,' and then enumerates the exact text attributes that can be modified. The word 'existing' implicitly distinguishes it from createTextLayer, and the text-specific scope separates it from broader layer-property 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 states what the tool does but gives no explicit guidance on when to use it versus alternatives such as createTextLayer, aiModifySelectedLayer, or setLayerProperties. There are no exclusions, prerequisites, 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?

No annotations are provided, so the description carries the full behavioral burden. 'Get list' implies a safe read and the PostScript qualifier usefully narrows the result set, but it never states whether the call is read-only, what the list contains (family names, styles, file paths), or whether ordering/pagination matters.

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. The verb and resource come first and the qualifying scope follows, so nothing needs to be skimmed past.

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 enumeration with no output schema, the description covers what the tool does and implicitly what it returns ('list of ... fonts'). It stops short of describing the shape of the returned entries, but that gap is minor for a tool this simple.

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 no parameter semantics to convey; the baseline for a parameterless tool is 4. The description correctly introduces no arguments.

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 (get), resource (fonts), and a meaningful qualifier (PostScript fonts registered in After Effects). No sibling tool deals with fonts, so differentiation is inherent, though the description never explicitly frames itself against alternatives.

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 trailing phrase 'for typography styling' gestures at context but gives no explicit when-to-use guidance, prerequisites, or alternatives. An agent must infer that this is the lookup step before creating or formatting text layers.

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 return shape (render engine, shader mode, list of available renderers), which is useful, but does not mention whether the operation is read-only, what happens if the comp doesn't exist, or any permission needs.

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. Slightly run-on due to the parenthetical enumeration, but every element is relevant.

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

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

No output schema exists, so the description helpfully names what is returned (engine, shader mode, available renderers). For a simple zero-required-param read tool with full schema coverage, this is nearly complete, though it omits any error or default-comp behavior 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% and the single compName parameter is documented with its default in the schema. The description adds nothing about parameter meaning, so the baseline 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 (get) and resource (composition 3D render engine and shader mode), and enumerates the possible engine values (Classic 3D, Advanced 3D, Cinema 4D). The get/set split from the sibling setCompRenderer is inferable but not named 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 statement of when to use this versus alternatives, no prerequisites, no note that it is a safe read operation. Usage is only implied by the 'get' verb.

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

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

With no annotations, the description carries the full behavioral burden. It does disclose the return content (parameter names, matchNames, types, values), which is genuine value beyond the schema, but says nothing about error behavior when the layer or effect is not found, or how the identifier parameters are resolved.

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 around the verb 'Inspect' with zero padding. It is efficient, though the enumerated return fields arrive in a dense list rather than being organized.

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 read-only inspection tool with no output schema and no annotations, the description conveys the shape of the return but leaves the identification model (five optional, seemingly redundant locator params) unexplained. Adequate but with a clear gap an agent would have to guess around.

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 all five parameters are already documented in structured data and the baseline of 3 applies. The description adds nothing about how compName/layerName/effectName/layerIndex/effectIndex combine to identify the target — notably, all five are optional with no stated resolution rule.

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

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

States a specific verb (Inspect) and resource (effect on a layer) and enumerates the returned attributes (parameters, matchNames, types, current values). It distinguishes itself implicitly from the mutation siblings applyEffect/setEffectProperties/removeEffect, but never names them or contrasts explicitly.

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

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

There is no statement of when to use this versus alternatives. The read-only nature is inferable from 'Inspect' amid a cluster of set/apply/remove siblings, but the description offers no condition, no prerequisite, and no exclusion to route 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?

With no annotations, the description carries the full burden. It is evidently a read-only documentation fetch and it discloses the categories of content returned, which is reasonable behavioral context for a harmless lookup, but it says nothing about whether the topic argument is optional or what a default call returns.

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

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

A single sentence, front-loaded with the verb and the resource, with no filler. Nothing could be trimmed without losing 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 one-parameter, optional-argument help tool with no output schema, the description is adequate but leaves gaps: it doesn't indicate that topic is optional or that a bare call returns general help, and it doesn't hint at what each topic yields. It is minimally sufficient rather than complete.

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

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

Schema description coverage is 100% and the enum fully enumerates the topic values, so the schema already documents the single parameter. The description adds nothing about the topic argument, so the baseline 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 ('Get') and enumerates the resource types returned (help, command list, property reference, troubleshooting guidance). It is clearly distinguishable from all sibling tools, which are AE mutation/query actions rather than documentation lookups, though it doesn't explicitly contrast itself with them.

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

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

Usage is implied by the tool's nature – an agent reaches for it when it needs documentation – but the description never states when to call it, what each topic covers, or when it is unnecessary. No alternatives or exclusions are named.

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 partially discharges this by disclosing that results include snapshot and rollback status, but it says nothing about ordering, pagination, or whether this is a read-only operation, leaving gaps for an unannotated 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?

A single front-loaded sentence that communicates the resource and key return contents with no filler. Appropriately sized for a one-parameter read tool.

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 paged read tool, the description covers the purpose and hints at return contents, but with no output schema and no annotations it should say more about the shape of the log entries or default behavior. Adequate but with visible gaps.

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

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

Schema coverage is 100% and the single 'limit' parameter is fully documented in the schema (default: 20). The description adds no parameter meaning beyond that, 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?

It names a specific verb (Get) and resource (execution history log of all operations performed via MCP), and adds scope detail about what the log contains (snapshot and rollback status). This is clearly distinct from the many mutation siblings, though it does not explicitly name a sibling it is not.

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 states what the tool returns but gives no when-to-use guidance, no conditions, and no alternatives. With siblings like 'rollback' and 'get-results' present, some routing context would help, but none is provided.

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

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

No annotations are provided, so the description carries the full behavioral burden. "Query" implies a read-only operation and the text discloses the return contents (effects, plugins, matchNames), but it does not explicitly confirm non-destructiveness, mention permissions, pagination, or 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?

A single efficient sentence with no waste, and the core purpose is front-loaded. It could be tighter given the somewhat list-like enumeration, but overall it is well-sized for a simple query tool.

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-optional-parameter read tool with no output schema and no annotations, the description partly compensates by naming the returned items (effects, plugins, matchNames), but it omits the read-only confirmation and any guidance on result shape or when to invoke it.

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

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

Schema description coverage is 100% and both parameters (search, category) are fully documented with examples in the schema. The description adds no syntax or format detail beyond what the schema already provides, so baseline 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 (Query) and resource (installed effects, plugins, matchNames in After Effects). The word "installed" distinguishes it from applied-effect siblings like getEffectProperties and setEffectProperties, though it never names those alternatives. Clear but lacks explicit sibling differentiation.

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

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

Usage is only implied: an agent can infer this is a discovery tool to run before applyEffect, but the description never says when to use it or when to prefer a sibling like getEffectProperties. No exclusions or prerequisites are stated.

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 full burden of behavioral disclosure. It indicates a read operation by saying 'Get detailed information', but does not mention any side effects, required permissions, or rate limits. The detailed list of returned fields adds some value but does not cover all behavioral aspects.

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, efficient sentence that front-loads the purpose and lists the key returned data. It is appropriately sized and structured for an API tool description, with no unnecessary 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?

There is no output schema, so the description should explain return values. It lists some returned fields (values, times, interpolation, speed/influence curves) which is helpful, but it does not cover all potential return data such as whether the keyframes are for multiple dimensions or contain additional metadata. Additionally, behavioral aspects like whether it requires a selected composition or layer are not mentioned. For a read tool with 4 parameters and no annotations, it is minimally complete but has gaps.

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

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

Schema description coverage is 100%, so the schema already documents all four parameters. The description does not add any meaning beyond what the schema provides; it only specifies what information is returned, not how parameters affect the output. 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 clearly states it retrieves detailed information on keyframes for a property, including specific data points like values, times, interpolation, and speed/influence curves. This distinguishes it from sibling tools like 'setLayerKeyframe' or 'getLayerInfo' by focusing specifically on keyframe details.

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 (to get keyframe info) but does not explicitly compare it to alternatives or state when not to use it. The context of sibling tools suggests it is for reading keyframe data, but no explicit guidance is provided.

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 burden. 'Get' strongly implies a read-only, non-mutating call and the description lists what is returned, but it never explicitly states read-only behavior, side effects, permissions, or output format. 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?

A single front-loaded sentence that opens with the verb and resource and keeps the field enumeration compact. No filler or redundancy, though the parenthetical list is slightly long.

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?

There is no output schema, so the description correctly compensates by naming the returned fields and both operating modes. For a low-complexity read tool this is nearly complete; only the safety/permission profile is left unstated.

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 baseline is 3, but the description adds meaning beyond the schema by clarifying that the optional layerName/layerIndex parameters are the switch between 'a layer' and 'all layers in a composition' — the schema only says 'optional' without explaining the omitted-case behavior.

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

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

States a specific verb (Get) and resource (layer information) and enumerates the returned fields (position, scale, rotation, 3D status, effects, masks), plus the dual scope of one layer vs all layers in a composition. It does not differentiate itself from the many get* siblings like getKeyframeInfo or getEffectProperties, so it stops short of a 5.

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

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

Usage is only implied: omitting layerName/layerIndex switches to 'all layers in a composition', which hints at when each mode applies. There is no explicit when-to-use, when-not, or named alternative among the dozens of get* siblings, so it sits at the implied-usage level.

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, and it does supply useful context about what data the call surfaces (the material/shader property set). However, it says nothing about whether the layer must already be a 3D layer, what happens if the layer is 2D, or permission/error behavior. It is a safe read by implication of 'Get', but no behavior is disclosed beyond that implication.

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

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

A single front-loaded sentence with the verb and resource first, followed by a compact enumeration. The parenthetical list is slightly long but it earns its place by substituting for a missing output schema.

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

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

For a simple three-parameter read tool this is close to adequate, and the parenthetical enumeration partially compensates for the absent output schema by naming the fields returned. It still lacks any indication of the return structure, error conditions, or 2D-vs-3D precondition, leaving modest gaps.

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

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

Schema description coverage is 100% and all three parameters (compName, layerName, layerIndex) are documented in the schema itself. The description adds no parameter-level meaning, so the baseline of 3 applies — the schema fully does the work.

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 ('Get') and resource ('3D material/shader options for a 3D layer'), and the parenthetical enumeration of the option categories (shadows, transmission, ambient, diffuse, specular, metal) concretely scopes what is returned. It is distinguishable from the sibling setLayerMaterialOptions, though the read-vs-write contrast is left implicit rather than stated.

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 when-to-use guidance, no statement of prerequisites, and no named alternative (e.g., 'call this before setLayerMaterialOptions to discover valid values'). The read-only intent of a 'Get' verb is inference, not instruction.

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 usefully discloses the return contents (file path, dirty status, compositions, items) in the absence of an output schema. However, it does not state that this is a read-only, side-effect-free operation, nor mention permissions or any behavioral limits.

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

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

A single front-loaded sentence with a colon-delimited list of return fields. No filler and nothing redundant.

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?

This is a simple zero-parameter getter, and since no output schema exists, the description does the work of naming the key return fields. It is largely sufficient, though it could spell out the return structure a bit more given the missing 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 tool takes zero parameters, so per the rubric the baseline is 4. There are no parameters whose meaning needs clarifying, and schema coverage is 100%.

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

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

The description states a specific verb and resource ('Get general project information') and enumerates the payload (file path, dirty status, compositions, items). This is clear enough to distinguish from layer-level getters like getLayerInfo or getSettings, though it does not explicitly name 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?

There is no when-to-use, when-not-to-use, or alternative-naming guidance. The agent must infer the use case purely from the enumerated return fields, and nothing tells it when to prefer this over getSettings, getHistory, or getLayerInfo.

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

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

No annotations are provided, so the description carries the full disclosure burden. It does not state what happens when no result exists, whether results expire or are cleared, the return shape, or error behavior — leaving the agent without any behavioral context for a read 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?

A single front-loaded sentence with no filler; the core action and both modes are stated immediately. It is efficiently sized, though it could carry more substance without becoming bloated.

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

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

With no output schema and no annotations, the description should describe what is actually returned (raw stdout, structured data, errors). It does not, so an agent cannot anticipate the response of this 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?

Schema coverage is 100%, and the schema already explains 'Specific command ID to retrieve, or omit for the latest result.' The description's mention of the latest result merely restates the schema, so the baseline 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 gives a clear verb-plus-resource ('Retrieve results of a previously executed command') and distinguishes the two retrieval modes (specific command vs. latest). It does not, however, differentiate itself from nearby siblings like getHistory or rollback, which an agent might confuse for retrieving prior execution output.

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 when-to-use or when-not-to-use guidance. The agent is left to infer that this pairs with a command-execution tool such as run-script, and no alternative (e.g. getHistory) is named or excluded.

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 returned content (settings plus connection status), which is genuinely behavioral information. However, it says nothing about whether this is a pure read, whether it can fail or hang when After Effects is not running, or what 'connection status' resolves to.

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; the purpose and scope are stated immediately.

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 read tool, the description covers what is retrieved and from where, which is enough to invoke it correctly. It could add a note on the diagnostic use case relative to configureSettings, but nothing essential is missing.

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

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

The tool takes zero parameters, so there is nothing for the description to disambiguate; baseline 4 applies.

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 ('Get') and two concrete resources ('MCP settings' and 'connection status to After Effects'). It is clearly distinguishable from the sibling configureSettings (read vs. configure), though it does not name that sibling explicitly.

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

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

There is no guidance on when to call this versus alternatives such as configureSettings, nor any precondition (e.g., that it is useful for diagnosing whether the bridge/AE connection is live). Usage is only implied by the verb 'Get'.

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 discloses the import formats and the optional layer-adding side effect, but says nothing about project-state mutation, whether re-importing duplicates footage, overwrite behavior, or undo semantics for what is fundamentally a write 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?

A single front-loaded sentence leading with the verb and the format list, then the optional layer behavior. Efficient, though the long format enumeration is dense; it is not bloated.

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

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

For an 8-parameter mutation tool with no annotations and no output schema, the description covers formats and the two operating modes but omits behavioral context (error handling on missing files, re-import behavior, return value). Adequate but with clear gaps.

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

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

Schema description coverage is 100%, so every parameter (name, scale, compName, filePath, isThreeD, position, sequence, convertToShape) is already documented in the schema. The description only touches compName's effect ('add as a layer in a composition') and adds no format/syntax detail beyond the schema, so the baseline 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?

Specific verb ('Import') plus resource ('assets into AE project'), with an explicit enumeration of supported formats (.obj/.gltf/.glb, images, SVG/AI, video, audio) and the optional layer-creation mode. This clearly distinguishes it from sibling creation tools like createSolidLayer or create3DLayer.

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 use case (bring external media into the project, optionally as a layer) but gives no explicit when-to-use/when-not guidance and names no alternatives. The optional-layer phrasing hints at the two modes but does not tell the agent which sibling to prefer or when.

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

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

No annotations are provided, so the description carries the full behavioral burden. It discloses the bundled FastSal-NIMA-Lite model, the luminance-cliff detector, and the four detection targets, but it does not state that the operation is read-only, describe side effects or failure modes, or explain the return format. It does not contradict any 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 front-loaded sentence that immediately names the action and resource, then lists the analyses performed. It is dense with model jargon but every clause earns its place by naming a detector or detection target; slight structural separation would improve readability, but it is not bloated.

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

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

This is a complex inspection tool with no annotations and no output schema, so the description should ideally explain return structure and operational constraints. It does list the detection targets and the NIMA score range, which helps an agent understand the purpose, but it omits the shape of the results, thresholds, and whether the operation is purely read-only. It is adequate for invocation but incomplete for interpreting results.

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% for the single imagePath parameter, and the schema already documents that it is an absolute path to a .png or .jpg frame. The description adds 'rendered After Effects frame' context but no additional path syntax, constraints, or alternatives beyond the schema. With the schema doing the heavy lifting, a baseline 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 gives a specific verb and resource: inspect a rendered After Effects frame (.png, .jpg). It clearly distinguishes this from sibling tools by focusing on frame-level visual inspection using a saliency/aesthetic model and boundary detector, and it names the concrete signals it returns.

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 context is clear enough to infer usage: inspect a rendered frame for clipping, occlusion, saliency, and aesthetic score. However, it never states when to choose this over siblings such as evaluateVideoWithDOVER or fixLayerGlowAndBoundsClipping, nor does it give exclusions or prerequisites. Usage is implied rather than explicitly guided.

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

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

With no annotations at all, the description carries the full burden, and it does disclose real side effects: it scans for AE installations, writes a .jsx file into the ScriptUI Panels directory, and performs automatic menu backup cleanup. It omits whether an existing install is overwritten, idempotency, required file permissions, and whether a restart is needed — significant gaps for a filesystem-mutating tool.

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

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

One sentence, front-loaded with the core action, with the backup-cleanup caveat tucked into a parenthetical rather than buried mid-sentence. Dense but no wasted clauses.

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

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

No output schema exists, so the description should say what comes back (e.g. which installations were detected, whether installation succeeded) and whether AE must be relaunched; it says none of that. For a one-parameter setup tool it is adequate but leaves real operational questions unanswered.

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 a single optional parameter with 100% schema description coverage ('Optional custom ScriptUI Panels directory path'), so the schema already does the work. The description adds the useful implication that the directory is auto-detected by default, but gives no format or example for the override.

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 (install) and resource (the mcp-bridge-auto.jsx panel script placed into ScriptUI Panels), plus the auto-detection step. It partially separates itself from siblings like cleanBridgeBackups by mentioning built-in menu backup cleanup, though it never names those siblings directly.

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

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

Usage is only implied: an agent can infer this is the setup step that must precede the bridge-dependent tools. There is no explicit 'use when' statement, no mention of prerequisites (e.g. whether After Effects must be closed or restarted), and no pointer to cleanBridgeBackups or rollback as alternatives.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions the new nested sub-composition and custom name but omits important mutation behavior: what happens to source layers, whether they are replaced or moved, how naming conflicts are handled, and whether the active composition is used by default.

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 wasted text. Its terseness is appropriate structurally, though it leaves behavioral gaps that are assessed elsewhere.

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

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

For a mutation tool with no annotations and no output schema, the definition is incomplete. An agent lacks sufficient context about side effects, required preconditions, and how the resulting precomp relates to the parent composition.

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 the parameters are already well documented. The description only echoes 'selected layers' and 'custom name' without adding clarity about the alternative layerNames/layerIndices inputs or the compName default.

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

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

The description states a specific verb and resource: precompose layers into a new nested sub-composition. It is clear what the tool does, but it does not differentiate itself from related composition-creation or layer-manipulation 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?

There is no guidance on when to use this tool versus alternatives, no prerequisites, and no explanation of how layerNames and layerIndices interact or should be chosen. The phrase 'selected layers' implies a selection workflow but does not clarify 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 full behavioral burden and fails it: it does not say whether removal is destructive/undoable, whether it errors when the named effect or layer does not exist, or what happens to keyframes and properties attached to the removed effect. For a mutation tool with zero annotation coverage 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 zero filler; the verb and target lead. It is arguably too terse given the mutation semantics, but there is no structural waste.

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

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

A destructive mutation with no annotations, no output schema, and no statement of success/failure behavior or side effects. Given the sibling context (applyEffect, setEffectProperties, reorderEffect), the agent needs at least a hint about preconditions and reversibility that the description never provides.

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 the five params (compName, layerName, layerIndex, effectName, effectIndex) are already documented, giving a baseline of 3. The description does not clarify the ambiguity inherent in the schema, namely that layer and effect can be addressed either by name or by index and that all five params are optional.

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 (Remove) and resource (effect from a layer), which an agent can act on directly and implicitly distinguishes it from applyEffect/addEffect siblings. It stops short of naming any sibling or scope constraint (e.g., effect must already exist on that layer), 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 when-to-use guidance, no prerequisites, and no mention of the obvious alternative family (applyEffect, reorderEffect, setEffectEnabled). The use case is inferable from the name alone, but the description itself adds nothing about context or exclusions.

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

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

No annotations are provided, so the description carries the full behavioral burden and discloses almost nothing beyond the bare action. It does not say what happens to layer references, expressions, or rendered output that point at the old name, whether the rename is undoable, or what error surfaces if the composition does not exist.

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

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

A single front-loaded sentence with zero waste. It is appropriately sized, though the terseness reflects missing information rather than disciplined editing.

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?

This is a mutation tool with no annotations and no output schema, so the description must cover behavior, and it does not. An agent cannot tell whether the operation is safe, reversible, or what it 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?

Schema description coverage is 100%, so both parameters are already documented in the schema, including the useful default that compName falls back to the active composition. The description adds no syntax, naming-constraint, or collision-handling detail beyond the schema, so baseline 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 ('Rename') and resource ('composition') with the host application named. It distinguishes itself from most siblings, but does not differentiate from setCompositionProperties, which could plausibly also rename a composition.

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 when-to-use guidance, no prerequisites, and no mention of alternatives such as setCompositionProperties. The agent must infer entirely from the name that this is the rename path.

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

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

No annotations are provided, so the description carries the full behavioral burden. It discloses only that this reorders within the effect stack, saying nothing about permissions, out-of-range index handling, whether the operation is reversible, or the response. For a mutation tool with zero annotation coverage this is a significant gap.

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

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

A single tight sentence with the action front-loaded and no wasted words. The trailing parenthetical adds marginal confusion rather than value, keeping it short of a 5.

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 6 parameters, no annotations, and no output schema, the description does not explain how to identify the target effect (name-based vs index-based params) or what newIndex must be. For this complexity level the description is too thin to fully guide a correct 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 100%, so all six parameters (including the two ways to identify the effect: layerName/effectName vs layerIndex/effectIndex) are already documented in the schema. The description adds no parameter meaning beyond that, which is the expected baseline 3.

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 ('Reorder an effect in the layer effect stack'), which clearly separates it from siblings like applyEffect, removeEffect, and setEffectProperties. However, it does not name a sibling it is not, and the parenthetical 'move up or down' slightly conflicts with the schema's absolute 'newIndex'.

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 alternatives such as setEffectProperties or applyEffect, and no prerequisites (e.g., effect must already exist on the layer). Usage is only implied by the verb 'reorder'.

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