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

With no annotations, the description fully discloses the mutative behavior (rendering video), side effects (output path), and specific processing like looping and ducking of BGM and loudness normalization. Lacks mention of required preceding steps or potential 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?

Single sentence efficiently packs all major operations in a natural, front-loaded order. Every clause adds 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?

Given the complexity of video assembly, the description covers key behaviors (Ken Burns, concat, captions, music, loudness). It mentions the return value (output path) but lacks details on output format or error conditions. Sufficient for an experienced 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?

Schema coverage is 75% (three of four parameters have descriptions). The description adds context for bgmPath ('looped, ducked') and mentions overall loudness normalization, but does not elaborate on bgmVolumeDb or captions beyond schema defaults. Adequate but not exceptional.

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

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

The description uses specific verbs ('Render', 'concat', 'burn in') and names all major processing steps: Ken Burns motion, caption burn-in, background music (looped, ducked), loudness normalization. It clearly distinguishes this as the final assembly step among sibling tools.

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

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

The phrase 'Render the final video' implies it is the terminal step after sibling tools like generate_narration and generate_images. The context is clear, but no explicit when-or-when-not to use or alternative suggestions are given.

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

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

No annotations are provided, so the description carries the full burden. It discloses behavioral traits: format dimensions and duration limits ('shorts' <60s) and what is returned (project id and quality guide). It does not mention authorization or side effects, but for a creation tool this is sufficient.

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 efficiently worded sentences. The first sentence states the purpose and key points; the second clarifies the return value. No redundant or unnecessary 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 5 parameters and no output schema, the description covers the key return value (project id and quality guide) and explains format choice. It could mention language defaults or voice, but those are covered in the schema. The description is complete enough for an agent to understand the tool's role and 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?

Schema coverage is 80%, so the baseline is 3. The description adds value by explaining the format enum with aspect ratios and duration constraints, which is not in the schema enum descriptions. It does not describe other parameters like title or voice, but those have schema descriptions. The added context for format justifies a 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 'Start a new faceless video project', identifying the verb and resource. It specifies the format options ('shorts' vs 'long') and mentions the return value (project id and quality guide), distinguishing it clearly from sibling tools that handle subsequent steps like set_script or generate_narration.

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 implicitly tells when to use (to start a project) by mentioning 'Returns the project id used by all other tools', indicating it's the first step. However, it does not explicitly state when not to use or provide alternatives, but the context is clear given sibling tools are later steps.

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

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

Without annotations, the description carries the full burden. It discloses that caption timing uses whisper timestamps when available, otherwise proportional, and that shorts get karaoke word-highlight. However, it does not mention that the captions are burned into the video (destructive), any prerequisites beyond narration, or error conditions. More context on side effects 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?

Three sentences: first defines purpose, second explains algorithm, third gives ordering hint. No redundant words. Front-loaded with the core action 'Build burned-in captions', making it efficient and scannable.

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

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

For a tool with 3 parameters and no output schema, the description provides key information: purpose, algorithm (timing method, karaoke), and execution order. It does not explain what 'burned-in' means or the effect on the project video, but the implication is reasonably clear. More details on prerequisites or output behavior would make it complete.

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

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

The schema covers 67% of parameters with descriptions (position and highlightColor). The description adds meaning beyond schema by explaining the timing algorithm and karaoke feature, which contextualizes the highlightColor parameter. It also clarifies that projectId refers to the project containing narration audio, providing semantics for the undocumented projectId 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 'Build burned-in captions from the narration audio', specifying a specific verb and resource. It distinguishes from sibling tools by mentioning 'Run after generate_narration' and noting the karaoke word-highlight feature for shorts, which sets it apart from other tools like generate_narration or assemble_video.

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 usage context by stating 'Run after generate_narration', establishing a dependency and ordering. However, it does not explicitly list alternatives or when not to use the tool, though no direct alternatives exist among siblings. The guidance is strong but lacks explicit exclusions.

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

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

No annotations are provided, so the description must bear full behavioral transparency. It mentions the model (CodexImage) and style appending, but fails to disclose whether the tool is destructive, what the output format is (URL vs file path), required permissions, or rate limits. The description is incomplete for a generative 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 highly concise with two sentences, no redundancy, and every word earns its place. It front-loads the core action and additional technical details follow naturally.

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 (2 params, no output schema, no annotations), the description covers core function and technical details but lacks completeness on output behavior, prerequisites, and error conditions. It is adequate for a simple generation tool but leaves gaps compared to best practices.

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 50% (sceneIds has a short description, projectId has none). The description adds meaning by explaining that one image is generated per scene and that project aspect ratio is used, which partially compensates. However, projectId remains undescribed, and sceneIds description in schema already states 'Regenerate only these scenes', so added value is modest.

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 'generate' and the resource 'one image per scene (or the listed sceneIds)'. It distinguishes from sibling tools like generate_thumbnail (single thumbnail) and generate_captions (different output). References to 'CodexImage' and 'project aspect ratio' further clarify the tool's specific function.

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 provide guidance on when to use this tool versus alternatives like generate_thumbnail, nor does it mention prerequisites (e.g., script must be set) or constraints (e.g., scene count limits). The usage context is implied but not explicit.

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

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

No annotations provided, so description carries full burden. Description does not disclose side effects (e.g., whether it modifies project state, overwrites existing narration), required permissions, or non-obvious behaviors like rate limits or cost implications.

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 short sentences, no redundant information. Front-loaded with the core action and scope. Every phrase is informative.

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

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

Description covers the basic function and return value, but lacks prerequisites (e.g., project must exist, script required?), error cases, and details about output format beyond durations. Given 3 parameters and no output schema, it is adequate but not complete.

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

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

Schema coverage is 67% (voice and sceneIds documented). Description adds value by explaining that sceneIds are for regeneration and that the tool returns per-scene durations, which is not in the schema. However, the voice parameter is not elaborated beyond override.

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

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

Description clearly states verb 'synthesize', resource 'narration audio', and scope 'for every scene (or the listed sceneIds)'. Distinguishes from sibling tools like generate_images and generate_captions which deal with other modalities.

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

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

Usage is implied by the tool purpose: use for generating narration audio. No explicit guidance on when to use or when not to use, nor alternatives. Sibling tools are not mentioned in the description.

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

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

No annotations provided, so description must carry full burden. It discloses the model (CodexImage), orientations, and text-free advice, but does not mention potential costs, idempotency, or how the generated thumbnail is stored/returned.

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

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

Two concise sentences front-loading the purpose and key constraints. 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 no output schema and no annotations, the description covers core functionality but omits return value or integration details (e.g., how to retrieve the thumbnail). Adequate for a simple generation tool but not fully complete.

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

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

Schema coverage is 50% (only prompt described). The description adds relevant guidance for prompt (dramatic subject, strong lighting), but projectId lacks any elaboration in both schema and description.

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

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

Clearly states it generates a text-free thumbnail via CodexImage with specified dimensions for landscape/shorts. Differentiates from siblings (create_project, generate_images, etc.) by targeting thumbnails specifically.

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 guidance on prompting (one dramatic subject, strong lighting) and advises adding text later, but does not explicitly state when to use this tool versus alternatives like generate_images 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?

With no annotations, the description carries the full burden. It discloses the read-only nature and the output format (name+id). It does not mention authorization or dynamic behavior, but for a simple list-like tool this is adequate and not contradictory.

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, short sentence that immediately conveys the purpose and result. Every word earns its place with no redundancy.

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

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

For a zero-parameter list tool, the description is complete: it states the action, the output (name+id), and the use case (picking a narrator). No output schema is needed as the description covers it.

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

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

There are zero parameters, so the baseline is 4. The description adds value by specifying what the tool returns ('name + id'), which goes beyond the empty schema. Schema coverage is 100% by default.

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

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

The description clearly states the tool lists available voicebox voice profiles (name + id) with the specific purpose of picking a narrator. It uses a specific verb ('list') and identifies the resource ('voicebox voice profiles'), and distinguishes itself from sibling tools like 'generate_narration' which would use the selected voice.

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 before 'generate_narration' to select a narrator, but does not explicitly state when not to use it or mention any alternatives. The context is clear for a simple list 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 provided. The description discloses that the tool replaces the existing script and returns pacing/quality warnings. However, it does not mention authentication needs, rate limits, or other side effects. Adequate but not exhaustive.

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 that are front-loaded with the purpose and followed by actionable guidance. Every sentence earns its place, no wasted words.

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

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

For a tool with two parameters and no output schema, the description covers the essential behavior (replace script, return warnings) and advises on next steps. It could mention the structure of the warnings or that it returns the full script, but overall it is sufficient.

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 already includes descriptions for the parameters (narration: 'keep under ~40 words', imagePrompts: '1-3 concrete visual moments...'). The tool description does not add additional meaning beyond what the schema provides. With schema coverage effectively high, a score of 3 is appropriate.

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

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

Description explicitly states it 'Set (or replace) the full scene list' with per-scene narration and image prompts. This clearly distinguishes it from sibling tools like generate_narration and generate_images which handle individual elements.

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 provides context: 'You are the writer — bring a hook, concrete details, and one idea per scene' and says to fix warnings before generating assets. It implies when to use (before generating) but doesn't explicitly contrast with alternatives or state when not to use.

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