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

With no annotations, the description carries full burden. It does not disclose any behavioral traits such as whether the marker is added to the active sequence, what happens if the time is out of range, or if the tool is destructive. Missing crucial info for an agent.

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

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

The description is a single sentence with no waste, but it is too brief given the tool's complexity (5 parameters). A more structured approach would improve clarity.

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 5 parameters, no output schema, and no annotations, the description is incomplete. It does not explain success behavior, marker representation, or how sequenceName works, leaving the agent with significant 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 0% and the description only adds meaning to the 'time' parameter ('seconds'). The other four parameters (name, comment, colorIndex, sequenceName) remain completely undocumented, leaving the agent without necessary context.

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

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

The description clearly states the action ('Add') and the resource ('marker to the sequence timeline'), and specifies the key parameter ('at a given time (seconds)'). It distinguishes this tool from siblings like 'clear_markers' and 'get_markers'.

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

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

No guidance on when to use this tool versus alternatives, no prerequisites, and no exclusions. The description only states what it does, not when to use it.

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

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

No annotations are present, so the description must disclose behavioral traits. It only states the action (add track) without mentioning side effects (e.g., track creation details, impact on existing tracks, required permissions, or error conditions).

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, concise sentence with no redundant words. It is front-loaded with the action and object, though it could benefit from additional context without sacrificing brevity.

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 tool with two parameters and no output schema, the description provides the core purpose but lacks contextual details like when to use, sequence selection, and behavioral constraints, leaving gaps for an AI agent.

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

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

The description adds meaning for trackType (video/audio) beyond the schema, but does not clarify the 'sequenceName' parameter. Since schema coverage is 50%, the description partially compensates but leaves ambiguity for half the parameters.

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

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

The description clearly states it adds a video or audio track to a sequence, which distinguishes it from sibling tools like add_marker or append_clip. However, it lacks specificity about which sequence (e.g., active sequence) and the context of use.

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

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

No guidance is provided on when to use this tool versus alternatives, such as when to add a track vs. insert a clip or apply an effect. The description does not mention prerequisites or typical use cases.

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 cover behavioral traits. It only states the basic append behavior, omitting error conditions (e.g., what if itemName doesn't exist), permissions, undo behavior, or any side effects. This is insufficient for safe autonomous invocation.

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 of 12 words with no unnecessary information. The key information (append to end of track) is front-loaded and immediately clear.

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 no output schema, no annotations, and 4 parameters with low schema coverage, the description is too brief. It fails to explain what the tool returns, error handling, prerequisites (e.g., item must be in project), or behavior when sequenceName is omitted. The tool complexity is moderate, but the description provides minimal 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 coverage is only 25% (trackType has description). The description does not add meaning to itemName, trackIndex, or sequenceName beyond their names and types. For example, it doesn't clarify that itemName must match an existing project item or how trackIndex is zero-indexed. The description only partially compensates for the low schema 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?

Description clearly states the action 'append' and the resource 'project item to track', with positional context 'after the last clip'. It distinguishes from siblings like insert_clip (which inserts at a specific position) and overwrite_clip (which replaces content).

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 for appending at the end of a track but provides no explicit guidance on when not to use or alternatives. Given siblings like insert_clip and overwrite_clip, the agent must infer the differentiation without explicit help.

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

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

With no annotations, the description carries full burden but only states that the tool applies an effect and requires QE DOM. It does not disclose side effects, error handling, or whether the effect uses default parameters, leaving significant behavioral gaps.

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 concise sentence without filler, but it lacks structural elements like parameter summaries or return info, which would improve readability.

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 5 parameters, no output schema, and no annotations, the description is insufficient. It does not cover return values, error states, or effect parameter control, leaving the tool's behavior largely undocumented.

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

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

Schema coverage is only 20% (just effectName has a description). The description adds no further explanation for clipIndex, trackIndex, trackType, or sequenceName, failing to compensate for the low 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?

The description specifically states 'Apply a video effect (by name) to a clip already on the timeline,' which clearly indicates the action and resource. However, it only mentions video effects while the schema supports audio tracks, causing slight ambiguity.

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

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

No guidance on when to use this tool versus alternatives like apply_transition. The only additional information is the requirement for Premiere's QE DOM, which is a prerequisite, not usage context.

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

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

Mentions dependency on Premiere's QE DOM and applies to clip edge, but does not clarify which edge (in/out), error behavior, or side effects. No annotations present to supplement.

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

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

Two concise sentences, front-loaded with core purpose and essential prerequisite. No wasted words.

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

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

Description omits critical details: which clip edge, return behavior, error handling, and no output schema. For a tool with 6 parameters and mutation side-effects, this is insufficient.

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 low (17%), and description adds minimal parameter context (only transitionName examples). Most parameters like clipIndex, trackIndex lack 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?

Description clearly states verb 'apply', resource 'video transition (by name)' and target 'clip edge on the timeline'. Differentiates from sibling 'apply_effect' by specifying transition vs effect.

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 vs alternatives like 'apply_effect'. No exclusion criteria or prerequisites beyond the brief mention of QE DOM.

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?

Description states the action but does not disclose side effects, error behavior, or reversibility. For a destructive tool with no annotations, more transparency is needed.

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, clear verb first, no superfluous words. Efficiently conveys the core action.

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

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

Given the tool has 1 param, no output schema, and no annotations, the description is incomplete: it lacks explanation of the parameter and behavioral details.

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 parameter 'sequenceName' is not described in the schema or the tool description. Agents cannot infer its meaning or format. Schema coverage is 0%, and the description provides no parameter 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?

The verb 'Delete' and resource 'all markers on a sequence' directly states the action. It distinguishes from siblings like 'add_marker' and 'get_markers'.

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 usage context provided. Does not specify when to use this tool instead of alternatives like 'remove_clip' or 'trim_clip'. No prerequisites or conditions mentioned.

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

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

The description does not disclose behavioral traits beyond the obvious 'create' action. There are no annotations to rely on, so the description should mention side effects (e.g., overwriting existing sequences) or permissions required, but it does not.

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 concise sentence that directly states the tool's purpose. It is front-loaded and efficient, though it sacrifices detail for brevity.

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

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

Given the lack of annotations and output schema, the description is too sparse. It does not explain what a sequence is, what the return value looks like, or any constraints, making it insufficient for an agent to use 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?

The description adds no meaning to the parameters. The schema has two parameters: 'name' (required, no description) and 'presetPath' (optional, described). The description does not elaborate on 'name' or clarify the purpose of 'presetPath', resulting in poor parameter 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?

The description states the tool creates a sequence, which is clear. However, it does not specify that this is a timeline sequence in the video editing context, which would further distinguish it from other sequence-related tools like 'set_active_sequence'.

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

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

No guidance is provided on when to use this tool versus alternatives. For example, it does not mention that 'set_active_sequence' is for switching sequences, not creating them. The description lacks any usage context.

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

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

No annotations are provided, so the description carries full burden. It mentions 'full access to the app/qe DOM' and 'shell,' implying power and risk, but lacks explicit warnings about potential crashes, irreversible changes, or performance impact.

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

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

Two front-loaded sentences with zero waste: the first defines the action and scope, the second adds usage restrictions.

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

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

For a single-parameter tool with no output schema, the description is adequate but could benefit from adding details about return values, error handling, and safety notes, given the tool's power.

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

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

The input schema has 0% description coverage for the single required parameter 'script.' The description adds 'ExtendScript (ES3 JavaScript)' but does not clarify whether it expects a code string, file path, or anything about syntax, encoding, or limits.

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 'Run arbitrary ExtendScript (ES3 JavaScript) inside Premiere Pro' — a specific verb and resource — and distinguishes it from siblings by noting it's for 'anything the other tools don't cover.'

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 explicitly says 'Use sparingly and only when a dedicated tool doesn't exist' and compares it to 'a shell into the running Premiere Pro instance,' giving clear when-to and when-not-to guidance.

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

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

No annotations are provided, so the description bears full responsibility. It does not disclose whether the operation is synchronous or asynchronous, whether it overwrites files, or any permission requirements. Only the basic action is described.

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

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

The description is a single, focused sentence that immediately conveys the core action. No superfluous words are present.

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

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

Given the lack of annotations and output schema, the description is too brief. It does not explain the export workflow, error conditions, or what the agent should expect after invoking 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?

The input schema covers 67% of parameters with descriptions (outputPath and presetPath). The tool description adds no additional parameter information beyond the schema, and the sequenceName parameter lacks any description.

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

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

The description clearly states the action ('queue/export'), the resource ('sequence to a media file'), and the method (using an Adobe Media Encoder preset). It distinguishes from sibling tools by specifying export functionality.

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

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

The description explains what the tool does but provides no guidance on when to use it versus alternatives. No exclusions or prerequisites are mentioned, though the context is clear.

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 provided, and the description does not disclose any behavioral traits (e.g., what happens if no markers exist, required permissions, side effects). The description carries the full burden but fails to provide these details.

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, concise sentence of 6 words with no waste. However, it may be too sparse for a tool with no 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?

No output schema, so the description should hint at return format. It does not. The parameter is not explained, and the tool's behavior in edge cases is omitted. Incomplete for a data-retrieval tool.

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

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

The schema has 0% description coverage. The description does not explain the parameter 'sequenceName' (e.g., is it a name or ID? required or optional?). No added meaning beyond the parameter name.

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

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

The description clearly states the verb 'list', resource 'markers', and scope 'on a sequence'. It distinguishes from sibling tools like add_marker and clear_markers by focusing on listing.

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

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

No guidance on when to use this tool versus alternatives. Does not mention prerequisites, such as whether the sequence must be active or if markers are always 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 provided; description does not disclose behavioral traits beyond the action. It implies read-only access, but does not mention prerequisites (e.g., a project must be open) or error conditions. For a parameterless tool, this is adequate but not comprehensive.

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

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

Single sentence, front-loaded with verb and resource, no wasted words. All information is presented efficiently.

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

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

No output schema, but description lists three return fields (name, path, sequences). For a simple info retrieval tool, this covers the main use case. Lacks details on edge cases or error handling, but acceptable given simplicity.

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?

No parameters exist (0 params, 100% schema coverage). Description does not need to add param info; baseline score of 4 is appropriate for a tool with no parameters.

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

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

The description clearly states the tool retrieves info about the currently open Premiere Pro project, listing specific fields (name, path, sequences). It distinguishes from sibling tools like get_markers or get_timeline_items which return different data.

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 by stating 'currently open project', but does not explicitly compare with alternatives or specify when not to use. Since it's a simple info tool, the context is clear but lacks explicit guidance.

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

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

No annotations provided, so description carries full burden. It discloses the tool is a read-only list operation and specifies output fields (times in seconds), but lacks details on behavior when sequenceName is omitted, ordering, 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?

Single sentence under 20 words is concise and front-loaded with core purpose. However, it could be slightly more structured by separating output details.

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 list tool, description covers basic purpose and output, but lacks information on how to specify the sequence, consequences of omitting parameter, and output structure (no output schema).

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

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

Schema description coverage is 0% and description only implicitly mentions sequenceName without describing its meaning, constraints, or whether it is optional. The parameter name alone provides insufficient semantic value.

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

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

The description clearly states the tool lists all clips on every track of a sequence with specific time properties (start/end/duration/in/out in seconds). It effectively distinguishes itself from sibling tools like get_markers or list_project_items.

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

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

No guidance on when to use this tool versus alternatives. It does not mention prerequisites (e.g., active sequence, required parameter) or when not to use it.

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

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

No annotations are provided, so the description carries the full burden. It only states basic import behavior without disclosing side effects, permissions, error conditions, or whether the operation is destructive. The example and file path mention add minimal context.

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 with 16 words, front-loading the key action and resource. No superfluous content; every phrase earns its place.

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

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

For a one-parameter tool without output schema, the description covers the core function and parameter meaning. However, it lacks information on return behavior, error handling, or expected outcomes, which could help the agent complete the task 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% with the 'paths' parameter already explained. The description adds media type clarification (video/audio/image) which is helpful but not critical. Baseline 3 is appropriate as the schema already provides meaning.

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

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

The description clearly states the verb 'import', the resource 'media files' including types, and the destination 'into the project panel' with method 'by absolute file path'. This distinguishes it from sibling tools like 'insert_clip' or 'list_project_items'.

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 for importing media into the project panel but does not explicitly state when not to use or suggest alternatives like timeline insertion tools. It provides implicit guidance through the destination phrase, but no direct 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?

With no annotations, the description must disclose behavioral traits. It mentions the ripple effect, which is useful. However, it omits details about preconditions (e.g., active sequence, existence of the item), error handling, or side effects on the timeline.

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, well-structured sentence that front-loads the core purpose and behavior. 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?

Given the complexity (5 parameters, no annotations, no output schema), the description is insufficient. It does not explain the return value (e.g., success/failure indicator), what happens on invalid input, or prerequisites like an active sequence.

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 60% (3 of 5 parameters have descriptions in schema). The tool description adds no extra meaning for the undocumented parameters 'trackIndex' and 'sequenceName' (no descriptions in schema or description). It does not clarify valid values or behavior beyond what the schema 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 uses a specific verb 'Insert' and clearly identifies the resource ('project item onto a track at a given time') and the key behavioral effect ('rippling later clips forward'). This distinguishes it from siblings like 'append_clip' or 'overwrite_clip'.

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

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

The description implies the tool is for inserting with ripple effect, but it does not explicitly state when to use this tool versus alternatives like 'append_clip' or 'overwrite_clip'. No when-not-to-use 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 provided, so description carries full burden. Describes that it returns all items with bin path, which is a read-only operation. No mention of performance or limits, but adequate for a simple listing.

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

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

Single sentence, front-loaded with key information (verb, resource, scope, detail). No redundancy or excess 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?

Tool is simple (0 params, no output schema). Description covers what the tool does and hints at output structure (bin path). Sufficient for an agent to invoke 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?

Tool has no parameters; schema coverage is 100% trivially. Baseline 4 applies as there is no need for param descriptions. The description adds no param info but none is needed.

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

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

Clearly states the verb 'List', the resource 'media items in the project panel', and adds scope 'all' and detail 'including their bin path'. Distinguishes from sibling 'get_timeline_items' which operates on timeline, not project panel.

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?

Implied usage for browsing project content, but no explicit when-to-use or when-not-to-use compared to siblings like 'get_timeline_items' or 'import_media'. No exclusion criteria.

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 provided, so description carries full burden. It says 'commonly available', which hints at filtering but doesn't clarify if all effects or just a subset. No mention of side effects (likely none), but could be more precise.

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

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

Single sentence, no unnecessary words, front-loaded with verb and resource.

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

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

Given zero parameters and no output schema, the description is sufficient. It links to apply_effect, providing necessary context for a simple listing 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?

No parameters, so baseline is 4. The description does not need to add parameter info; schema coverage is 100% trivially.

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 the tool lists video effect names and that these are used with apply_effect. Distinct from sibling tools like apply_effect which applies effects.

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?

Implies usage before calling apply_effect, but does not explicitly state when to use or not use versus alternatives. Still clear enough for most agents.

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 fully disclose behavior. It states 'move' and 'does not ripple', but omits details like what happens if the target time is occupied (overlap handling), scope (all track types), or whether the operation is reversible. Partially transparent.

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

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

The description is a single concise sentence, but it sacrifices completeness for brevity. It does not address parameter semantics or provide usage context, making it under-informative despite being short.

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 5 parameters, no output schema, and no annotations, the description is insufficient. It only covers basic purpose and a key behavioral trait, leaving parameter roles, return values, and error conditions 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 only 20% (only trackType has a description). The tool description does not explain any of the 5 parameters, leaving meaning ambiguous for clipIndex, trackIndex, newStartSeconds, and sequenceName.

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

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

The description clearly states the verb 'move' and resource 'timeline clip', and specifies the action: to a new start time on the same track. It also notes a key constraint ('does not ripple other clips'), which distinguishes it from siblings like insert_clip that cause rippling.

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 for moving clips without affecting adjacent clips, but it does not explicitly state when to use this tool versus alternatives (e.g., insert_clip for rippling moves). No direct guidance on prerequisites or limitations.

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?

Without annotations, the description carries full burden. It discloses key behaviors: overwriting existing content and no ripple. However, it omits details such as whether the overwritten clip is deleted, undo behavior, return values, or required permissions. Adequate but not thorough.

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 words. It efficiently conveys the core action and key behavior. Could be slightly improved with structured lists, but remains concise and clear.

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

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

Given the complexity of overwriting in a timeline and the existence of sibling tools (append, insert, move), the description lacks details like return values, error conditions, what happens to the overwritten clip, and the role of the optional sequenceName parameter. Incomplete for a mutation tool.

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

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

The input schema has 5 parameters with only 20% coverage (trackType described). The description adds no additional parameter details, failing to compensate for low schema coverage. It only implicitly references itemName, track, and time without explaining their formats or constraints.

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

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

The description clearly states the verb 'Place' and the resource 'a project item onto a track at a given time', with the specific behavior of overwriting and no ripple. This distinguishes it from sibling tools like append_clip and insert_clip, though not explicitly naming 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 description implies usage context (overwriting with no ripple) but provides no explicit guidance on when to use this tool versus alternatives like insert_clip or append_clip. No when-not-to-use or prerequisite information is given.

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

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

No annotations are provided, and the description does not disclose behavioral traits such as destructive nature, permission requirements, or whether the removal is undoable. The ripple parameter is not mentioned in the description.

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 efficiently states the tool's primary purpose. However, it could include key parameter behavior without becoming verbose.

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 5 parameters (3 required) and no output schema or annotations, the description is too brief. It omits the effect of the ripple parameter, sequence handling, and return values, leaving significant 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?

The description adds meaning to trackIndex and clipIndex by referencing get_timeline_items, but does not explain ripple, trackType, or sequenceName. With schema coverage at 40%, more detail is needed.

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

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

The description clearly specifies the action ('Remove a clip') and the resource ('from the timeline'), and references get_timeline_items for indices, distinguishing it from sibling tools like move_clip or trim_clip.

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 hints at usage by referencing get_timeline_items for indices but does not explicitly state when to use this tool over alternatives or exclude cases like unprotected sequences.

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 full behavioral disclosure. It only states 'Save the currently open project' without mentioning whether it overwrites the existing file, requires a path, or prompts for confirmation. This is insufficient for a mutation action.

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 concise single sentence that front-loads the action and resource. It is efficient, though it could be slightly expanded to include key behavioral details without becoming verbose.

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

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

Given the tool's simplicity (0 params, no output schema), the description is minimally complete. However, it lacks context about save behavior (e.g., automatic overwrite, file path) which would be helpful for an agent to avoid user prompts or errors.

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

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

The tool has no parameters (0 params), so the description need not add parameter details. The baseline of 4 applies as there is no missing parameter information.

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

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

The description clearly states the action ('Save') and the resource ('the currently open project'). It is specific and unambiguous. However, it does not differentiate from sibling tools, though the context of saving is distinct from editing operations like add_marker or append_clip.

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 is provided. The usage context (saving a project) is implied by the name and description, but there are no prerequisites, exclusions, or warnings about unsaved changes.

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 provided, so description carries full burden. It states state change (makes active) but omits side effects, permissions, or behavior if sequence doesn't 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?

Single sentence, no redundant words, front-loaded with action and context.

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

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

For a simple tool with one parameter and no output schema, description covers core purpose. Could mention prerequisite that sequence must exist, but adequate overall.

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

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

Only parameter 'name' is not described beyond schema type; schema coverage 0% means description adds no meaning about what name expects (e.g., full path or display name).

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

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

Description clearly states the action (make active), the resource (existing sequence), and the context (timeline panel), distinguishing it from siblings like create_sequence.

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?

Implies usage for selecting a sequence to display in the timeline panel. No explicit alternatives or exclusions, but the simple action doesn't require them.

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 provided, so description carries full burden. It only mentions 'without removing it' but lacks detail on side effects, permissions, or state transitions (e.g., what happens when already disabled).

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

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

Single sentence, concise, front-loaded with key information. 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?

With 5 parameters, no output schema, and no annotations, the description is insufficient. It does not explain how to use parameters, what disabled=true/false does, or provide complete context for a non-trivial 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 only 20%; only trackType has a description. The overall description does not explain parameters like disabled, clipIndex, trackIndex, or sequenceName 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 clearly states the verb (enable/disable) and resource (a clip on the timeline), and distinguishes from sibling tools like remove_clip by stating 'without removing it'.

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

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

No guidance on when to use this tool vs alternatives. Sibling tools include move_clip, trim_clip, etc., but the description does not differentiate usage context.

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

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

No annotations are provided, so the description must fully disclose behavior. It only states that in/out points are changed in seconds, but does not reveal potential side effects (e.g., clipping beyond source duration), whether parameters are optional, or the effect of omitting inSeconds/outSeconds.

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

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

The description is a single sentence that conveys the core action and unit without extraneous words. It is well-structured for quick comprehension.

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 6 parameters (3 required) and no output schema, the description is too sparse. It does not explain how parameters interact, valid ranges, or whether inputs are relative or absolute. An agent needs more detail to use the tool 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 only 17% (only trackType has a description). The description adds no meaning for the parameters; it mentions 'in/out points' but does not map them to 'inSeconds' or 'outSeconds', nor explain 'clipIndex', 'trackIndex', or 'sequenceName'. It fails to compensate for the low 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?

The description clearly specifies the action ('trim head/tail'), the resource ('timeline clip'), and the unit ('seconds of source media time'). It effectively distinguishes from sibling tools like 'move_clip' or 'remove_clip' by focusing on in/out point modification.

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

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

The description provides no guidance on when to use this tool versus alternatives, such as 'move_clip' or 'apply_effect'. It lacks context about prerequisites or scenarios where trimming is appropriate.

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