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

No annotations are provided, so the description must convey behavioral traits. It only states the basic action ('Add'), without disclosing side effects, permissions, or whether the composition is created from scratch or from a file. This is insufficient 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?

The description is very short (two lines) and minimally structured. While concise, it sacrifices clarity and completeness. Every sentence earns its place, but more details would improve it.

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 annotations and an output schema that is not provided, the description lacks essential context. It does not explain what a Fusion composition is, how to specify it, or what the result is. The tool is complex enough to require more detail.

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 groups the three parameters as a 'Clip locator', adding conceptual meaning beyond the schema's types and defaults. However, individual parameter semantics are not explained, and coverage is 0% in the schema, so the description partially compensates.

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), resource (Fusion composition), and target (timeline item). It does not explicitly differentiate from similar siblings like 'insert_fusion_composition', but the purpose is unambiguous.

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

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

No guidance on when to use this tool versus alternatives (e.g., import_fusion_comp, insert_fusion_composition). No prerequisites or context provided, leaving the agent to guess the appropriate scenario.

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 burden of behavioral disclosure. It only states the basic action and lists parameters, but does not disclose side effects (e.g., overwriting existing markers), required permissions, error conditions, or return 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?

The description is extremely concise: a single sentence for purpose followed by a bullet-style parameter list. Every sentence provides necessary information without redundancy. It is front-loaded and 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?

Given the lack of annotations and the presence of an output schema (not shown), the description is moderately complete. It covers parameter semantics well but lacks usage context such as prerequisites (e.g., timeline must exist), edge cases, or what the tool returns. With 6 parameters and a clear action, more context would be helpful.

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, so the description must compensate. It provides meaningful descriptions for all six parameters, including a list of valid colors and default values for duration. While some parameter descriptions could be more precise (e.g., exact string format for color), the description adds significant value beyond the schema titles and types.

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 explicitly states the verb 'Add' and the resource 'a marker to the current timeline'. It differentiates well from sibling tools like get_markers (which retrieves) and add_fusion_comp (which adds a different element).

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. There is no mention of prerequisites, conditions for use, or exclusions. The agent is left to infer usage context from the tool name alone.

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 fails to disclose important behavioral traits. It implies a state change (adding to queue) but does not clarify if the addition triggers immediate rendering, whether the tool is idempotent, or if there are any side effects (e.g., on existing jobs). With no annotations provided, the description carries the full burden of disclosure, which is not met.

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 of appropriate length, front-loading the key verb and resource. Every word serves a purpose, with no redundancy or irrelevant 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?

Given the tool's simplicity (zero parameters) and the presence of an output schema (which reduces need to explain return values), the description is minimally adequate. However, in the context of many sibling tools with overlapping functionality, the description does not provide enough context about how this tool fits into the rendering workflow (e.g., sequential steps). A more complete description would note that render settings must be configured beforehand.

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

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

The tool has zero parameters, so per rubric baseline is 4. The description does not add any parameter-specific meaning beyond the schema, but that is acceptable since schema coverage is 100%. No further clarification is needed for 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 action ('add a render job') and the resource ('to the queue') with a condition ('based on current render settings'). This verb+resource+condition combination makes the purpose unambiguous. However, it does not differentiate from siblings like 'start_rendering' or 'set_render_settings', which might overlap in 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?

No guidance is provided on when to use this tool versus related siblings. The description does not mention prerequisites (e.g., need to set render settings first) or the typical workflow (e.g., after adding, one might need to start rendering). This omission leaves the agent uncertain about the correct 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?

With no annotations, the description must disclose behavioral traits but only notes that clips 'must exist'. It omits what happens if no timeline is open, clip names are invalid, or how errors are handled.

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 extremely concise—two sentences that front-load the purpose and immediately list the parameter. Every sentence is necessary and efficient.

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

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

Given the tool's simplicity (1 parameter) and no annotations, the description partially covers needed context (parameter meaning, existence requirement) but lacks details on preconditions (e.g., open timeline), edge cases, and return value behavior (output schema exists but unused).

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% (no parameter descriptions in schema), but the description adds meaning: 'clip_names: List of clip names to append (must exist in the current media pool folder)', which clarifies parameter semantics beyond the schema's bare title.

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 specifies the verb 'append' and resource 'media pool clips to the current timeline by name', clearly distinguishing it from sibling tools like 'create_timeline' or 'add_marker'.

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 should be used when clips already exist in the media pool and a timeline is active, but it does not explicitly state prerequisites or when alternatives like 'import_media' might be preferred.

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 must fully disclose behavior. It only states the tool creates a clip, without mentioning side effects (e.g., changes to timeline), required permissions, or performance impact. The behavioral scope is minimal and insufficient.

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 concise: a one-line purpose followed by a structured parameter list. Every sentence adds value. No unnecessary words or repetition.

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

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

Given the tool has 3 parameters and no required fields, the description covers parameter semantics adequately. However, it lacks usage context (e.g., when to use versus siblings) and does not describe return values, though an output schema exists. Overall, minimally complete but with 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 beyond the input schema by explaining each parameter with defaults and behavior (e.g., '1-based track index', 'list of 0-based item indices'). Schema coverage is 0%, so the description compensates well, though not exhaustively.

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 creates a Fusion clip from timeline items. The verb 'create' and resource 'Fusion clip' are specific. The phrase 'from one or more timeline items' distinguishes it from related tools like 'add_fusion_comp' which may add a new 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 guidance is provided on when to use this tool versus alternatives. There is no mention of prerequisites, context, or situations to avoid. The parameter descriptions offer defaults but no strategic usage advice.

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 discloses that the tool is AI-powered and requires a specific software version, which is helpful. However, it does not describe whether the operation is destructive, how performance is impacted, or error scenarios (e.g., if Neural Engine is unavailable). Additional behavioral context would improve transparency.

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 concise with two sentences plus a parameter list. The main purpose is front-loaded. It could be slightly more structured (e.g., grouping prerequisites), but overall it is efficient without 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?

The output schema exists, so return values need not be explained. The description covers prerequisites and parameter roles. However, it lacks discussion of error handling, resource impact, or expected behavior when prerequisites are not met. For a creation tool with 4 parameters, it is adequate but not thorough.

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

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

Schema description coverage is 0%, so the description must compensate. It explains the 'mode' parameter with allowed values ('F', 'B', 'BI') and groups 'track_type/track_index/item_index' as clip locators. This adds meaning beyond the raw schema, though detailed semantics of each mode (forward, backward, bidirectional) are not fully elaborated.

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 'Create an AI-powered Magic Mask on a timeline item for subject isolation' with a clear verb and resource. It also notes a prerequisite (DaVinci Resolve Studio with Neural Engine). While it does not explicitly differentiate from the sibling 'regenerate_magic_mask', the distinction is implied by the verb 'create' versus 'regenerate'. Purpose is clear and specific.

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 a prerequisite (DaVinci Resolve Studio with Neural Engine) but provides no explicit guidance on when to use this tool versus alternatives like 'regenerate_magic_mask' or other timeline tools. Usage context is implied but lacks exclusions or comparisons.

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. It lists parameters and defaults but does not disclose side effects, output format, or behavior when audio is missing, limiting transparency.

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 concise, front-loaded with the main purpose, and lists parameters efficiently without 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 5 optional parameters and an output schema (not shown), the description covers parameter details and a version requirement but lacks information on return values or potential side effects, leaving some 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?

Despite 0% schema description coverage, the description adds meaning by listing all language options, explaining chars_per_line range and default, and clarifying preset options, which goes beyond the schema property names.

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

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

The description clearly states the tool generates subtitles from audio using AI speech recognition, which distinguishes it from siblings like transcribe_audio and transcribe_and_add_subtitles.

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 includes a version requirement (DaVinci Resolve Studio 19+), providing some usage guidance, but does not explicitly state when to use this tool versus alternatives 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 present, so the description must cover behavioral traits. It only states creation without mentioning side effects, required state, or return value (despite an output schema existing). Destructive potential or impact on current selection 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?

The description is very short and to the point, but it sacrifices necessary detail. Every sentence is minimal, but the lack of additional context reduces usability.

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 annotations, the description is adequate but incomplete. It fails to explain output or behavioral implications, and the existence of an output schema is not leveraged.

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 merely repeats the schema's parameter name and adds 'Name for the new timeline', which adds negligible meaning. Schema coverage is 0% because the description does not elaborate beyond the parameter's title.

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 creates a new empty timeline in the current project, using a specific verb and resource. It is distinct from sibling tools like append_to_timeline or get_current_timeline_info.

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, or any prerequisites like needing an open project. The description is purely declarative.

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 only implies a destructive action but lacks details on undoability, required permissions, or side effects beyond the minimum.

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?

Description is short and front-loaded with purpose. Parameter list is clear but could be slightly more streamlined without losing 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?

The tool has an output schema (not shown) which may cover return values, but the description omits success/error handling and prerequisites. For a simple delete operation, it's minimally adequate.

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

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

Schema description coverage is 0%, but the description adds meaning for all 4 parameters (e.g., comp_name defined as 'Name of the Fusion composition', track_type et al. as 'Clip locator'). This compensates well for the gap.

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

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

The description clearly states the verb 'Delete' and the resource 'a named Fusion composition from a timeline item', which is specific and distinguishes it from sibling tools like add_fusion_comp or rename_fusion_comp.

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 (e.g., when to delete vs rename a composition). No prerequisites or when-not-to-use context 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 burden. It does not disclose whether the tool is read-only or if it modifies the timeline (e.g., adds markers). The behavioral impact is unclear.

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 extremely concise with two sentences, no wasted words, and the key action is front-loaded. Every sentence earns its place.

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

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

Given that an output schema exists, the description could be sparser, but it omits any mention of what the tool returns or whether it has side effects. With no annotations, more context is needed for a complete understanding.

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, and schema coverage is 100%. The description adds no parameter information, but with zero parameters, the baseline is 4 as it does not need to compensate.

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 detects scene cuts using AI on the current timeline. It uses a specific verb and resource, and it is distinct from sibling tools like add_marker or smart_reframe.

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 prerequisite of DaVinci Resolve Studio, giving some context, but does not explicitly state when to use this tool versus alternatives or when not to use it. The usage is implied but not fully 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?

No annotations provided, so description carries the burden. It discloses pre-loaded namespace variables and that timeline may be None, and explains output using print() or 'result' variable. However, it lacks details on error handling, side effects, or restrictions on code length or safety.

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?

Concise yet informative: states purpose, lists pre-loaded variables, explains output, and describes the parameter. Well-organized with bullet points. No unnecessary sentences.

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?

Adequate for a simple tool with one parameter and an output schema. Covers basics but could benefit from examples or clarification of error handling. Given the complexity of executing arbitrary code, more context would improve usability.

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

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

Schema coverage is 0%, so description must add value. It describes 'code: Python code to execute' and adds context about pre-loaded variables and output methods, which partially compensates. Could be more detailed about acceptable code syntax or limitations.

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?

Clear verb+resource: 'Execute arbitrary Python code' in the DaVinci Resolve scripting environment. Distinguishes from siblings by stating 'for operations not covered by specific tools,' making it a fallback tool.

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

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

Explicitly says 'Use this for operations not covered by specific tools,' implying when to use and when not to. Could be stronger by directly stating 'Prefer specific tools when available,' but still provides good 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 carries full burden. It does not disclose whether the export is destructive, if it overwrites existing files, or if it requires specific permissions. The description only mentions the parameter but no 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 very short and front-loaded, with no wasted words. However, it could expand slightly without losing conciseness to improve completeness.

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 (single parameter) and presence of output schema, the description is minimally adequate. It lacks details about synchronization, file overwrite behavior, or limitations, but covers the basic purpose.

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

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

The description adds value by listing the supported file extensions (.png, .jpg, .tif, .dpx, .exr), which are not present in the schema. However, it does not explain path requirements (e.g., absolute vs. relative, directory must exist). Schema coverage is 0%, so description compensates partially.

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 'Export' and the resource 'current frame', and lists supported file formats. However, it does not differentiate from the sibling tool 'screenshot', which may have overlapping 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?

No guidance on when to use this tool over alternatives like 'screenshot' or 'get_current_thumbnail'. The description lacks context about 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?

With no annotations provided, description carries full burden. Only states that it exports, but omits details on file format implications, overwrite behavior, permissions, or error handling. Minimal disclosure beyond basic 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?

Description is concise and front-loaded with the main action. Bullet list of parameters is clear, though could benefit from more structured formatting like tables.

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 has 5 parameters and no annotations. Description does not explain output schema, default behavior for optional parameters, or error conditions. Lacks completeness for an agent to confidently invoke the tool without additional assumptions.

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

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

Schema description coverage is 0%, so description must compensate. Bullet list repeats parameter names with trivial clarifications (e.g., 'Destination file path'), adding little meaning beyond the schema field names. Does not specify formats, constraints, or relationships.

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 (export) and resource (Fusion composition from a timeline item to a file). Distinguishes from sibling tools like import_fusion_comp or add_fusion_comp.

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. Does not specify prerequisites or conditions for use, leaving the agent without context for selection.

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 must fully disclose behavior. It only states the core function without detailing side effects (e.g., file overwrite behavior), resource requirements, supported audio formats, or error conditions. This is minimal disclosure for a file-writing 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?

The description is concise, front-loading the core purpose in the first sentence, followed by a parameter list. It avoids fluff, though the parameter list formatting could be slightly improved for readability. Overall efficient but not maximally polished.

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

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

The description covers the basics for using the tool but lacks contextual details like file overwrite behavior, supported audio formats, error handling, or return value description (though output schema exists). Given the presence of an output schema, the description is adequate but not comprehensive for a file-modifying 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 description adds meaning beyond the schema (which has 0% property descriptions) by explaining each parameter's purpose: 'Absolute path', 'Where to save', 'Whisper model size', 'Language code or None for auto-detect', 'Optional vocabulary/style hint'. This provides essential context not available from the schema alone.

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 transcribes audio and saves as an SRT subtitle file for import into Resolve. This specific verb+resource combination distinguishes it from sibling tools like 'transcribe_audio' (returns text) and 'transcribe_and_add_subtitles' (directly adds to timeline).

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 exporting SRT files but does not explicitly state when to use this tool vs alternatives. No mention of prerequisites, limitations, or when not to use it. The mention of Resolve import is helpful but insufficient for clear decision-making.

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 disclose behavioral traits. It does not mention whether the tool overwrites existing files, requires an open project, or is destructive. The output schema exists but is not described, nor are potential side effects 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 extremely concise with a clear sentence followed by structured parameter bullets. Every sentence provides necessary information without 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?

The description covers parameter choices but lacks information about return values, behavioral expectations (e.g., file overwrite), and prerequisites. Given the output schema exists but is not described, the description is moderately 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?

With 0% schema description coverage, the description adds meaning by listing export_type values and clarifying export_subtype for AAF and EDL. However, it does not explain the purpose or behavior of each export type (e.g., what 'drt' means), leaving some ambiguity.

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 'Export' and the resource 'current timeline to a file', providing a specific purpose. It distinguishes from sibling tools like 'export_current_frame' or 'export_fusion_comp' by focusing on timeline export.

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 (e.g., export_current_frame for images). The description lists export types and subtypes but does not explain trade-offs or provide usage context, leaving the AI to infer usage.

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 implies read-only behavior but does not explicitly state lack of side effects or permissions needed. Adequate but could be more 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?

Single sentence, 7 words, perfectly concise and front-loaded.

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 getter with no parameters and an output schema present, the description provides sufficient 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?

No parameters exist in the schema, so the description correctly doesn't add param info. Baseline 4 applies since 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 clearly states the specific verb 'Get' and the resource 'currently active page', which distinguishes it from siblings like 'open_page'.

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

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

No explicit when-to-use or when-not-to-use guidance is given, but the tool's purpose is self-evident; however, explicit usage context is lacking.

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 prerequisite (Color page, clip selected) but does not describe the return format or side effects. For a read-only tool with no parameters, this is adequate but minimal.

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

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

Two sentences, no extraneous information. Every word 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?

Given no parameters, no output schema, and no annotations, the description is fairly complete. It could mention that the thumbnail is returned directly, but the purpose is clear.

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, and schema coverage is 100%. Per guidelines, a baseline of 4 applies. The description adds no parameter info because none exist.

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 (get thumbnail), specific resource (current frame), and location (Color page). It distinguishes from siblings like 'screenshot' and 'export_current_frame' by specifying the context.

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 a clear precondition: must be on Color page with a clip selected. This implicitly tells when to use the tool. However, it does not explicitly mention when not to use it or suggest alternatives, which would improve clarity.

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

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

With no annotations, the description must carry the burden of behavioral disclosure. It states the operation is a read, but does not elaborate on return format, error handling, or behavior when no playback is active. The simplicity mitigates this somewhat, but more detail would be beneficial.

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, clear sentence that gets straight to the point with no extraneous information. It is front-loaded and efficient.

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

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

Given the tool has no parameters and an output schema exists (per context signals), the description is adequately complete. It communicates the core function without needing additional 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?

The tool has zero parameters. Per the rubric, this earns a baseline of 4. The description does not need to add parameter-level detail since there are none.

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 the current playhead timecode, using a specific verb-resource pair. It distinguishes itself from the sibling tool 'set_current_timecode' which performs a write operation.

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

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

No guidance is provided on when to use this tool versus alternatives. For instance, it does not mention that other tools like 'get_current_timeline_info' might also return timecode information, nor does it specify prerequisites or error conditions.

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

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

No annotations are provided, and the description does not disclose any behavioral traits such as being read-only, requiring permissions, or affecting state. The output schema exists but is not referenced or explained.

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, concise and to the point, with no unnecessary words. It is appropriately front-loaded.

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 simplicity (zero parameters) and presence of an output schema, the description is still incomplete by not specifying what 'detailed information' entails. It fails to leverage the output schema to explain return values.

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

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

There are no parameters, and the schema description coverage is 100% (empty). The description adds minimal meaning—'detailed information' is too vague. Baseline 4 is not justified because the description should compensate for the lack of parameter cues.

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 'Get detailed information about the current timeline' clearly states the verb and resource, but it is vague and fails to differentiate this tool from sibling tools like get_markers or get_current_timecode. The purpose is understood but lacks specificity.

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. With many sibling tools for specific timeline information, the description should indicate that this is a general overview tool.

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

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

No annotations are provided, so the description must fully disclose behavior. It only states it gets compositions, but does not mention that it is read-only, what happens if no comps exist, whether it returns full details or just names, or any side effects. This is minimal disclosure for a tool with no 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 very concise: two sentences. However, it could be better structured with a clearer separation of purpose and parameters. It lacks front-loading of critical info like return type.

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 with an output schema (likely covering return format), the description is adequate but leaves gaps. It does not specify what a 'Fusion composition' object contains or behavior in edge cases. Given the output schema exists, a score of 3 is appropriate.

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

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

Schema description coverage is 0%, so the description must compensate. It groups the three parameters as 'Clip locator', which adds some meaning, but it does not explain each parameter individually (e.g., valid values for track_type, meaning of index defaults). The added value is minimal.

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 all Fusion compositions for a timeline item. It uses a specific verb 'Get', identifies the resource 'Fusion compositions', and the scope 'associated with a timeline item'. This distinguishes it from sibling tools like add_fusion_comp (adds) or delete_fusion_comp (deletes).

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. There is no mention of when not to use it, prerequisites, or comparisons with similar tools like get_timeline_items or get_fusion_comp (if it exists). The description only states what it does without 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 correctly states the read operation ('Get') but does not disclose additional traits like return format, error conditions, or permission requirements. Minimal but adequate.

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 immediately conveys the purpose. Every word earns its place with no extraneous 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?

Given the tool has zero parameters and an existing output schema, the description is complete for its simplicity. It fully captures what the tool does without needing more detail.

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, so schema description coverage is 100%. Baseline is 4 according to rules. The description adds no parameter info, which is fine.

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 'Get' and the resource 'all markers on the current timeline.' It is specific and distinguishes from sibling tools like get_current_page or get_current_timecode.

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 clear context by specifying 'on the current timeline,' but lacks explicit when-not-to-use or alternative suggestions. For a simple parameterless tool, this is acceptable.

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; the description only restates parameter defaults (max_depth, max_clips) already in the schema. Does not disclose performance implications, read-only nature, or potential large responses despite having an output 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?

Extremely concise and front-loaded: a single sentence plus parameter list. No superfluous words, but additional context (e.g., return structure) is missing.

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 simplicity of the tool (2 optional parameters, no required fields, output schema exists), the description minimally covers the purpose and basic constraints. However, it lacks any note on performance or that it might return large data, leaving some completeness 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 merely repeats parameter names and defaults from the schema without adding semantic context (e.g., what values are valid, how max_depth affects recursion, or the meaning of limiting clips per folder). Schema description coverage is 0%, so the description fails to compensate.

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 the folder/clip structure of the media pool, using the verb 'get' and specifying the resource. This distinguishes it from sibling tools like get_current_timeline_info or get_project_info.

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 (e.g., get_project_info for project-level data, or import_media for adding files). Lacks explicit when/when-not or alternative recommendations.

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. The description adds the prerequisite but does not disclose other behavioral traits like read-only nature, error handling, or what happens if conditions are not met.

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 extremely concise: one line for purpose, one for prerequisite, and a bulleted list of parameters. No redundant 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?

Given the tool has an output schema, the description does not need return details. It covers prerequisite and parameter definitions but lacks context about error conditions or output 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 0%, so the description fully compensates by explaining each parameter with allowed values and indexing conventions, adding 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 clearly states the tool gets color grading node graph info for a timeline item, with a specific prerequisite. It is distinct from siblings, which are mostly different actions.

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 a clear prerequisite (must be on Color page with clip selected) but does not explicitly mention when not to use or alternatives. However, no similar tool exists among 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?

No annotations are provided, so the description carries the burden. It implies a read-only operation by listing what is returned, but does not explicitly state that the tool does not modify the project or disclose any other behavioral traits. It is acceptable 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?

Two concise sentences: first states the verb and resource, second lists the returned information. Every sentence is necessary and there is no wasted 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?

Given no parameters and an existing output schema, the description adequately explains what the tool returns in human-readable terms. It is complete for a simple info retrieval tool with no side effects.

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

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

There are no parameters in the schema, so the description has no parameter burden. It adds value by detailing the output content beyond what the output schema might provide, earning baseline 4.

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 gets information about the current DaVinci Resolve project, using a specific verb+resource. It lists the type of data returned (name, settings, timeline count, etc.), distinguishing it from sibling tools like get_current_timeline_info.

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 retrieving project information but provides no explicit guidance on when to use this tool vs. alternatives or any prerequisites. It is adequate for a straightforward info retrieval tool but lacks depth.

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 the description carries full burden. It explains the conditional parameter behavior but does not explicitly state that the operation is read-only or safe. The 'Get' verb implies non-destructive, but not clearly.

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

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

Two sentences with no redundancy. First sentence captures purpose, second explains parameter behavior. Every word earns its place.

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

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

For a simple query tool with an output schema, the description covers the essential behavior and parameter effect. No additional context is necessary given the tool's low 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?

With 0% schema description coverage, the description adds significant meaning: it explains the purpose of the render_format parameter and its effect on the output. However, it could specify allowed value formats.

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

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

The description clearly states the tool retrieves render formats and codecs, with a specific verb and resource. It distinguishes from siblings like get_render_settings and get_render_status.

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

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

No guidance on when to use this tool versus alternatives. The description does not mention prerequisites, context, or provide exclusions, leaving the agent without decision support.

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 indicates a read-only operation but lacks details on safety, auth requirements, or side effects. With no annotations, it carries the full burden but only offers minimal behavioral info.

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 'Get', no unnecessary words. Every part of the description adds value.

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

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

Given zero parameters and an output schema, the description adequately lists what is retrieved. However, it could clarify the scope ('current project timeline') or mention that it aggregates multiple 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?

No parameters exist, so the baseline is 4. The description does not need to further clarify parameter meanings, but it also does not explain what the returned data structure contains.

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 'current render format, codec, render job list, and render presets', distinguishing it from sibling getters like get_render_formats and get_render_status.

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

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

No explicit guidance on when to use this tool vs alternatives. While it implies collecting multiple render settings at once, it does not provide exclusions or context like when to use get_render_formats for just the format list.

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

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

No annotations are provided, and the description does not disclose behavioral traits such as what happens if the job ID is invalid, whether the call is idempotent, or any rate limits. The description only states the basic function.

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

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

The description is short and front-loaded with the purpose. Including the parameter list is somewhat redundant with the schema, but the additional context about job_id's origin is valuable.

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 an output schema, the description covers the essential usage. However, missing behavioral transparency reduces completeness.

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 the single parameter by explaining that job_id is obtained from add_render_job. This compensates for the 0% schema description 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 states 'Get the status of a render job' with a specific verb and resource. This distinguishes it from sibling tools like add_render_job, start_rendering, and stop_rendering.

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 notes the job_id is 'returned by add_render_job', providing clear context for when to use the tool. However, it does not explicitly state when not to use it or compare with 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?

With no annotations, the description must disclose behavioral traits but only states 'Get all properties', implying a read operation. It does not explicitly state that the tool is non-destructive or that no modifications occur. Given the absence of annotations, this is insufficient.

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 concise: a single sentence for the purpose followed by a clean list of parameters. It is well-structured and front-loaded, with no wasted words.

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

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

Given the existence of an output schema, the description need not detail return values. The parameter descriptions are complete, but it could mention that the output schema contains the properties. Overall, it is mostly complete for a read 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 description coverage is 0%, so the description compensates by explaining each parameter: track_type (video/audio/subtitle), track_index (1-based), item_index (0-based), and their defaults. This adds meaning beyond the schema which only provides titles and defaults.

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

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

The description states 'Get all properties of a specific timeline item', which clearly identifies the action (get) and resource (properties of a specific timeline item). It effectively distinguishes from sibling tools like 'get_timeline_items' (which gets items) and 'set_timeline_item_property' (which sets properties).

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 'get_timeline_items' or 'set_timeline_item_property'. The description lacks explicit context for when to use or not use this tool.

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

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

With no annotations provided, the description carries full burden for behavioral disclosure. It only states it lists items, omitting whether it's read-only, any permissions required, or side effects. The lack of annotation coverage leaves the agent inferring behavior.

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

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

Two sentences and a compact bullet list for parameters. Every sentence adds value with no filler. Front-loaded: immediate action and object.

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 presence of an output schema, the description need not detail return values. For a simple list tool, it covers the essentials (what, how to specify track). Minor gap: no mention of behavior when track doesn't exist or timeline is empty, but output schema likely covers structure.

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?

Input schema has 0% description coverage, but the description adds full meaning: track_type with allowed values and default, track_index with 1-based indexing and default. This compensates for the schema gap, though it could be more explicit about constraints (e.g., integer 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?

The description clearly states 'List all clips/items on a specific track of the current timeline,' identifying the specific verb (list) and resource (items on a track). It distinguishes from sibling tools like get_current_timeline_info or get_timeline_item_properties, though not explicitly, but the purpose is unambiguous.

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

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

No guidance on when to use this tool vs alternatives. It does not mention prerequisites (e.g., timeline must exist) or scenarios where alternative tools like get_timeline_item_properties (for a specific item) might be preferred. The description is purely operational.

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 fails to mention error conditions, side effects, or what happens if the track does not support voice isolation, leaving significant 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 extremely concise with two sentences and a parameter line, front-loading the essential action without any superfluous 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?

Despite the presence of an output schema (not shown), the description fails to clarify the return value or error states, making it adequate but not complete for a tool with no annotations.

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

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

The single parameter 'track_index' is described as '1-based audio track index', adding over the schema's 'type: integer' and 'title', and compensating for 0% schema description 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 states the action ('Get') and the resource ('Voice Isolation state for an audio track'), distinguishing it from the sibling 'set_voice_isolation_state' tool.

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 includes a prerequisite ('Requires DaVinci Resolve Studio') but does not explicitly state when to use this tool over alternatives, though the context of a simple getter implies use for reading state.

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 for behavioral disclosure. It only states the action without mentioning side effects, error handling, permissions, or what happens if the file doesn't exist. The output schema exists but is not described, leaving behavior opaque.

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 concise, front-loading the purpose with a single sentence followed by parameter explanations. No redundant information, but it is somewhat terse. Structure is clear and prioritizes key 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?

Given the tool's complexity (importing a file into a timeline item) and lack of annotations, the description is incomplete. It omits important context such as supported environments, file validation, output behavior, and potential constraints (e.g., must have an open project). The output schema exists but is not referenced.

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

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

Schema coverage is 0%, so description must compensate. It adds meaning by specifying comp_path as an absolute path to .comp or .setting file and describing track parameters as a 'Clip locator'. This provides context beyond raw schema, but defaults and exact semantics (e.g., what item_index=0 means) are missing.

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

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

Description clearly states the tool imports a Fusion composition from a file into a timeline item, identifying the verb and resource. It distinguishes from siblings like 'load_fusion_comp' (likely into media pool) and 'insert_fusion_composition' (different action). However, it could be more explicit about the exact timeline context.

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. There is no mention of prerequisites, which timeline is targeted, or clarification on when import vs. load is appropriate. The description lacks usage context entirely.

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 whether files are overwritten, supported formats, file size limits, or success/failure behavior. It only states the basic action and parameter.

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 extremely concise: two short sentences plus a parameter list. It is front-loaded with the purpose, and every sentence serves a clear function without redundancy.

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

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

For a simple import tool with one parameter, the description covers the basic action and parameter but lacks details about return values, file type support, error handling, or behavior on duplicates. It is minimally adequate but not comprehensive.

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 description coverage is 0%, so the description must add value. It specifies that file paths must be 'absolute', which is not in the schema. This adds useful semantic context for the only parameter.

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

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

The description clearly states the tool's action ('import media files') and the destination ('into the current media pool folder'). It distinguishes from sibling tools like import_fusion_comp, which import compositions, and other import/export 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 indirectly implies usage for importing media files into the media pool, but does not explicitly state when to use this tool over alternatives, nor does it provide conditions 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 provided, so description carries full burden. It only states basic action, missing details like prerequisites (timeline must be open), side effects (does it overwrite?), or what happens at timeline end.

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 wasted words, front-loaded with key 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?

Lacks preconditions (open timeline, valid playhead) and return value info despite output schema existing. Adequate for simple action but incomplete.

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, schema coverage 100%. Description adds context about what is inserted and where, meeting baseline for 0-param tools.

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

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

Description clearly states the verb 'Insert', resource 'blank Fusion composition', and location 'into the current timeline at the playhead'. It distinguishes from sibling tools like add_fusion_comp, insert_fusion_generator, etc.

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: when you want to insert a blank Fusion comp at the playhead. No explicit when-not or alternatives compared to siblings like add_fusion_comp.

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. However, it only mentions insertion at the playhead, omitting side effects (e.g., overwriting), required context (e.g., existing timeline), and error conditions. This is insufficient for a tool with no structured behavioral hints.

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

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

The description is short and front-loaded with the essential purpose. The parameter list is redundant with the schema but doesn't harm conciseness. It could be more structured (e.g., separate behavior from parameter details) but is effective.

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 there is an output schema (unknown content), the description doesn't explain return values. For a simple tool with one parameter, the description covers the basic operation but lacks context about prerequisites (e.g., timeline existence, playhead position) and error handling, making it minimally adequate.

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

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

The schema has 0% description coverage, so the description must add meaning. It says 'Name of the Fusion generator to insert,' which provides more context than the schema's title alone, but it still lacks details like valid values, format, or required format. This is minimal added 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 action ('Insert'), the resource ('Fusion generator'), and the location ('current timeline at the playhead'). This specific verb+resource combination distinguishes it from siblings like 'insert_fusion_composition' and 'insert_fusion_title'.

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, no prerequisites, and no exclusions. It simply states what it does without helping an agent decide when to invoke 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 must disclose behavioral traits. It mentions insertion at the playhead but does not clarify side effects (e.g., whether it overwrites existing items, requires a specific track, or needs the timeline to be active). This is insufficient 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?

The description is concise with two sentences, front-loading the purpose. Every sentence is necessary, but a slight restructure could include parameter details more explicitly. Still, it achieves efficiency.

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

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

Given the tool's simplicity (one parameter, output schema present), the description covers the core functionality. However, it omits usage context, error conditions, and prerequisite checks, which would be helpful for a complete understanding.

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

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

The schema has 0% description coverage, so the description must compensate. It explains that 'title_name' is the 'Name of the Fusion title template to insert', adding meaning beyond the schema's 'Title Name'. However, it lacks additional helpful context like valid sources or formatting.

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 ('Insert a Fusion title'), the resource ('Fusion title'), and the context ('into the current timeline at the playhead'). It distinguishes itself from siblings like 'insert_fusion_composition' and 'insert_fusion_generator' by specifying 'title' 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 provides no guidance on when to use this tool versus alternatives, no prerequisites (e.g., must have an open timeline), and no mention of error cases or limitations. It only states the basic action.

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 does not explicitly state that the operation is read-only or has no side effects, but the action 'List' implies a safe query. No behavioral details beyond the purpose are given, which is sufficient for a simple listing 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?

The description is a single, clear sentence with no wasted words. It front-loads the verb and directly states what is listed and what is provided.

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 parameters, presence of an output schema (which handles return value documentation), and the straightforward nature of a listing operation, the description is complete and sufficient for an agent to understand and invoke the tool.

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

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

The tool has zero parameters, and the schema coverage is 100%. The description adds no parameter-specific information, but baseline for zero parameters is 4 as per calibration guidelines.

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 available mlx-whisper models with their HuggingFace repo paths, using a specific verb ('List') and resource ('mlx-whisper models'). It distinguishes itself from sibling tools like 'transcribe_audio' by focusing on model discovery rather than usage.

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 does not explicitly state when to use this tool versus alternatives like transcribing tools. While it's implied that one should list models before transcribing, no explicit guidance or exclusions are 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 the description must disclose side effects or state changes. It only states 'load as active composition' without explaining overwrites, requirements, or errors.

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 brief (two sentences plus parameter list) with no redundant information, but could include more context 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 no annotations and 4 parameters, the description lacks usage context, error handling, and behavioral details. Output schema exists but return values are still not explained.

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

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

Schema coverage is 0%, so the description adds parameter descriptions: 'comp_name: Name of Fusion composition' and clip locator terms. However, it does not explain allowed values for track_type or the meaning of clip locator indices.

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 'Load a named Fusion composition as the active composition' with a clear verb 'load' and resource 'Fusion composition', distinguishing it from siblings like import_fusion_comp or delete_fusion_comp.

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 (e.g., import_fusion_comp), no prerequisites, and no conditions for appropriate usage.

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

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

Annotations are absent, so description must carry behavioral disclosure. It only states the basic action without mentioning side effects, permissions, or limitations (e.g., whether it changes the application state or requires a loaded project).

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

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

The description is short and to the point, including a parameter list that aids usability. It could be slightly more concise but avoids unnecessary verbiage.

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

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

Given the tool's simplicity (one parameter, straightforward action), the description provides enough to understand and use it. However, it doesn't mention that an output schema exists or what the tool returns (likely nothing or a status). The completeness is adequate 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?

The input schema provides a bare string parameter with no enum or description (0% coverage). The description compensates by explicitly listing the valid page values ('media', 'cut', etc.), adding crucial meaning for correct invocation.

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 switches to a specific page in DaVinci Resolve, listing valid page names. This distinguishes it from sibling get_current_page which retrieves the current page.

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 get_current_page or when switching is appropriate. The agent receives no context on prerequisites or consequences.

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 only says 'regenerate', implying modification, but does not disclose side effects, what happens if no mask exists, or any destructive 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?

The description is short with one sentence and a parameter list, but the list does not add detail beyond the schema. It is minimally acceptable but could be more concise or structured better.

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 3 parameters with no schema descriptions, no annotations, and an output schema not mentioned, the description is incomplete. It lacks details on what regenerating entails, expected output, or error conditions.

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

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

Schema description coverage is 0%, so the description must compensate. It adds only 'Clip locator' as a label for the three parameters, which provides minimal context and does not explain each parameter's meaning or constraints (e.g., valid values for track_type).

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

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

The description clearly states the verb 'regenerate' and the resource 'existing Magic Mask on a timeline item'. It distinguishes the operation from creating a new mask implicitly, but does not explicitly differentiate from the sibling tool 'create_magic_mask'.

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 like 'create_magic_mask'. There is no mention of prerequisites (e.g., mask must exist) 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?

With no annotations, the description should disclose behavioral traits. It does not mention what happens if old_name is not found, whether changes are reversible, or any side effects on the timeline item.

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

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

The description is short and uses bullet points for clarity, though it lacks explanatory sentences. It is appropriately sized but could be better 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?

Given the complexity (5 parameters, 2 required) and the presence of an output schema, the description omits details on return values, error states, and when renaming is valid. It feels incomplete.

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

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

Schema coverage is 0%, so the description must add meaning. It briefly labels parameters but fails to explain track_type, track_index, and item_index beyond 'Clip locator', leaving ambiguity.

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 'Rename' and the resource 'Fusion composition on a timeline item', and it distinguishes from sibling tools like 'add_fusion_comp' and 'delete_fusion_comp'.

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, nor any prerequisites or exclusions. The description simply lists parameters without 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 provided, so description carries full burden. It discloses that the tool captures the Resolve window directly and works on any page, which is sufficient for a simple screenshot tool. Slight deduction for not mentioning output format or potential side effects, but for this tool it's minimal.

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?

Three sentences, each earning its place: purpose, usage, scope. Front-loaded with action. No extraneous 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 simple screenshot tool with no output schema, the description covers what, when, and scope. Complete and actionable for an agent.

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

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

Tool has zero parameters, so no parameter docs needed. Description does not need to add parameter-level detail. Baseline 4 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?

Description clearly states the tool takes a screenshot of DaVinci Resolve to see the current state. It explicitly specifies 'Captures the Resolve window directly. Works on any page.' which distinguishes it from sibling tools like get_current_thumbnail.

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

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

Provides explicit usage guidance: 'Call this frequently — before and after changes, when the user describes something visual, or whenever you need to verify what's on screen.' It tells the agent exactly when to invoke this tool.

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

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

No annotations are provided, so the description should disclose behavioral traits. It fails to mention whether the operation is destructive, requires specific permissions, or has side effects. Only parameter listing is insufficient.

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 uses a clear bullet list for parameters, but the initial sentence 'Apply CDL...' is brief. The parameter details are front-loaded and no unnecessary 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?

Despite having an output schema (context indicates true), the description offers no return value information. For an 8-parameter mutation tool, more context about results, side effects, or usage examples is needed.

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

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

Schema description coverage is 0%, so the description must compensate. It provides default values and format hints for RGB parameters (space-separated strings) but does not explain the purpose of each parameter beyond their names.

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

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

The description clearly states 'Apply CDL (Color Decision List) values to a node.' This is a specific verb-resource combination that distinguishes it from siblings like set_lut.

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 such as set_lut. The description misses context like 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?

Without annotations, the description only states the basic effect (moving the playhead). It fails to disclose important behavioral details such as side effects, reversibility, error handling for invalid timecodes, or required permissions, leaving the agent with significant unknowns.

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 extremely concise, with the purpose stated in the first sentence and parameter format immediately following. Every sentence adds value; there is no unnecessary 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?

Given the tool's simplicity (single parameter) and the presence of an output schema (though not shown), the description covers the essential behavior and parameter format. It could mention what happens on success or failure, but it is still effective for basic usage.

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 crucial meaning beyond the schema by specifying the timecode format ('HH:MM:SS:FF'), which the schema lacks (only type string). With 0% schema coverage, this provides the necessary guidance for correct parameter use.

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 ('Move') and the resource ('playhead'), making it distinct from sibling tools like 'get_current_timecode' which reads the timecode. It leaves no ambiguity about what the tool does.

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 setting the playhead to a specific timecode but does not provide explicit guidance on when to use it versus alternatives (e.g., when to use get_current_timecode instead) or any prerequisites like having a timeline open.

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 the action and lists parameters. It does not disclose behavioral traits like whether existing LUTs are replaced, side effects, or required permissions.

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 very concise: one sentence stating purpose followed by a structured parameter list. Every part adds value without redundancy.

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

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

Given the presence of an output schema, the description does not need to explain return values. It adequately covers the tool's operation, though it lacks context on node graph behavior or prerequisites. Still, it is complete enough for a simple parameterized action.

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?

With schema description coverage at 0%, the description adds valuable context for parameters (e.g., '1-based node index', 'absolute path to LUT file', defaults). It explains the parameters beyond the schema's type/title, though some details (e.g., allowed formats for lut_path) are missing.

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

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

The description clearly states the action ('Apply a LUT to a node in a clip's color node graph'), using a specific verb and resource. It distinguishes from sibling tools like 'set_cdl' by specifying LUT application.

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 a basic purpose but does not explicitly state when to use this tool versus alternatives (e.g., set_cdl) or provide context on prerequisites or conditions. No when-not-to-use guidance.

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

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

With no annotations provided, the description must disclose behavioral traits. It only says 'Configure,' which implies mutation, but fails to clarify if changes are applied immediately, require a restart, or have side effects. No mention of permissions, validation, 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 concise: a single introductory sentence followed by a bulleted list of parameters. It is front-loaded with the purpose, and each line contributes useful information. Minor redundancy (e.g., 'Format string' could be omitted) but overall efficient.

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

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

Given the tool has 3 optional parameters and an output schema (not described), the description covers most essential details for basic use. However, it lacks information on default behaviors, interaction between parameters (e.g., must render_format and codec be set together?), and what the tool returns or how it affects the project state.

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

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

The schema has 0% description coverage, so the description compensates by listing common keys for 'settings' and examples for 'render_format' and 'codec'. This adds significant meaning beyond the schema's minimal titles, though it doesn't explain all possible parameters or their exact formats.

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

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

The description clearly states the tool's purpose: 'Configure render settings for the current project.' It uses a specific verb ('Configure') and resource ('render settings'), and distinguishes from siblings like 'get_render_settings' and 'start_rendering' by focusing on the configuration step.

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 that this tool is used before rendering to set parameters, but it does not explicitly state when to use it versus alternatives. No guidance on prerequisites, exclusions, or scenarios where other tools (e.g., 'set_project_info') might be more appropriate.

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 only mentions that property_value is auto-converted, but does not disclose side effects, whether the change is immediate, or any permissions required.

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 concise with a clear opening sentence and a bullet-like parameter list. It is well-structured and easy to scan, though slightly verbose with the list formatting.

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 parameter count and the existence of an output schema, the description covers input semantics well but does not explain the output or error handling. It is adequate but missing context on behavior upon success/failure.

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?

With 0% schema description coverage, the description adds significant value by listing parameter names, providing examples for property_key, explaining type conversion for property_value, and stating defaults for track_type, track_index, and item_index.

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 ('Set') and the resource ('property on a specific timeline item'). It is specific and distinguishes from sibling tools that add, get, or delete 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 usage guidelines are provided. There is no indication of when to use this tool versus other property-related tools (e.g., get_timeline_item_properties) or alternatives for bulk updates.

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 burden. It only states that the tool isolates speech from background noise but does not disclose any side effects, destructive behavior, or other behavioral traits beyond setting parameters.

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 concise (4 lines), front-loaded with the purpose, and every sentence provides essential information without 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?

The tool has only 3 parameters and an output schema (implied from context). The description adequately covers purpose, prerequisites, and parameter details. No additional information is needed.

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%, but the description adds meaning by explaining track_index as 1-based, enabled as True/False, and amount as 0-100 with default 100. This goes beyond the schema's type and title.

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 'Set' and the resource 'Voice Isolation' with the specific purpose of isolating speech from background noise. The sibling list includes get_voice_isolation_state, making the distinction clear.

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

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

It mentions the prerequisite 'Requires DaVinci Resolve Studio' but does not explicitly state when to use this tool versus alternatives (e.g., get_voice_isolation_state for querying). Usage context is implied rather than 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?

With no annotations, the description must fully disclose behavioral traits. It only says 'Apply Smart Reframe' without explaining whether the operation is destructive, reversible, or what side effects occur. The AI-based nature is mentioned but lacks detail on constraints or outcomes.

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

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

The description is short and front-loaded, but underinformative. Every sentence is necessary but could be expanded 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 complexity of AI-based reframing and the presence of an output schema not mentioned, the description is incomplete. It lacks information about prerequisites (beyond Neural Engine), return values, or error conditions.

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%, but the description groups parameters as 'Clip locator', adding minimal meaning. However, it fails to explain each parameter's role or acceptable values, leaving ambiguity for an AI agent.

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 applies Smart Reframe to a timeline item, identifying it as AI-based reframing. The purpose is specific and distinct from sibling tools like stabilize or create_magic_mask, though no explicit differentiation is provided.

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 Smart Reframe versus other tools or alternatives. The only mention is a prerequisite (DaVinci Resolve Studio with Neural Engine), which is necessary but insufficient for usage decisions.

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 the description carries full burden. It fails to disclose behavioral traits such as whether the stabilization modifies the clip in place, is reversible, or has side effects. The requirement for DaVinci Resolve Studio is mentioned but is not sufficient to understand the tool's 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?

The description is concise with two sentences, front-loading the primary purpose. The second sentence lists the parameters, which is acceptable but could be more structured. Overall, it is appropriately sized.

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

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

The tool has 3 parameters and no annotations, and the description does not mention return values or output behavior. Although an output schema exists (not shown), the description lacks completeness for a stabilization operation, such as whether it succeeds silently or returns a status.

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%, but the description groups the three parameters as 'Clip locator', providing context that they identify a timeline item. However, it does not explain each parameter individually (e.g., what track_type values are valid). This adds some meaning beyond the bare 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 'apply stabilization' and the resource 'timeline item', specifying the technology 'DaVinci Neural Engine' and the requirement for DaVinci Resolve Studio. It distinguishes from siblings like 'smart_reframe' which is a different operation.

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

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

The description mentions a prerequisite (DaVinci Resolve Studio) but does not provide guidance on when to use this tool versus alternatives, nor does it specify scenarios where stabilization is appropriate or not.

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 must carry full burden. It does not disclose whether rendering is asynchronous, blocking, or what happens if already rendering.

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?

Extremely concise with two short paragraphs, front-loaded with main purpose, 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?

Adequate for a simple tool with one optional parameter, but lacks mention of output/return value and any side effects, given no annotations and an output schema exists.

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?

Description adds meaning beyond schema: clarifies that null job_ids renders all queued jobs, which is not evident from schema alone.

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 verb 'Start' and resource 'rendering queued jobs', distinguishing it from sibling tools like stop_rendering or get_render_status.

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

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

No guidance on when to use this tool versus alternatives, such as after queuing jobs or prerequisites for rendering.

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 must cover behavior. It omits what happens if no rendering is running, whether it blocks, or any 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?

One short, direct sentence with no wasted words; perfectly concise.

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?

Lacks details on return value (despite output schema existing) and edge cases like no running processes, but is sufficient for a simple stop action.

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?

With zero parameters, the description adds all meaning beyond the empty schema, stating the action clearly.

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 'stop' and the resource 'render processes', distinguishing it from siblings like 'start_rendering' and 'get_render_status'.

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

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

No explicit when-to-use or alternatives are given, but the simple action implies calling it to halt rendering when needed.

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