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. While it mentions the tool 'Run[s] a Gemini session' and lists configuration parameters, it doesn't describe what the session entails, whether it's interactive or single-turn, what happens to the conversation state, authentication requirements, rate limits, or error behavior. The description provides basic functional information but lacks important behavioral context for a tool with 7 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 appropriately sized and front-loaded with the core purpose. The first sentence establishes what the tool does, followed by relevant configuration details. There's minimal wasted text, though the parameter listing could be more concise given the schema already documents them thoroughly. Overall structure is logical 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?

For a tool with 7 parameters, no annotations, no output schema, and siblings with similar names, the description is incomplete. It doesn't explain what a 'Gemini session' entails, how it differs from sibling tools, what the expected behavior/output is, or important operational constraints. The comparison to Codex helps but doesn't compensate for the significant gaps in behavioral and contextual information.

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

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

Schema description coverage is 100%, so the schema already documents all 7 parameters thoroughly. The description lists the parameters and mentions they 'match the Codex Config struct', which adds some conceptual context. However, it doesn't provide significant additional semantic meaning beyond what's already in the schema descriptions. The baseline of 3 is appropriate when schema does the heavy lifting.

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

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

The description clearly states the tool 'Run[s] a Gemini session' and specifies it uses 'Google Gemini 3 Pro Preview', which is a specific verb+resource combination. However, it doesn't explicitly distinguish this tool from its siblings (gemini-image, gemini-reply, gemini-video-check, gemini-video-generate), which appear to be specialized variants. The comparison to 'Codex' provides helpful context but doesn't fully differentiate from 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 description implies usage context through the comparison to 'Codex' and mentions configuration parameters, but provides no explicit guidance on when to use this tool versus its siblings or alternatives. There's no mention of prerequisites, typical use cases, or when-not-to-use scenarios. The implied context is helpful but incomplete.

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 of behavioral disclosure. It does well by explaining cost implications (~$0.04/image), model performance characteristics (fast/cheap vs better text rendering), and auto-detection behavior. However, it doesn't mention rate limits, authentication requirements, or error conditions. For a generative AI tool with no annotations, this is strong but not comprehensive behavioral context.

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

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

The description is efficiently structured with clear sections: purpose statement, model comparison, auto-detection logic, and parameter summary. Every sentence earns its place by providing essential information without redundancy. The information is front-loaded with the core purpose and model options before parameter details.

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

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

For an image generation tool with 5 parameters, 100% schema coverage, and no output schema, the description provides strong contextual information about model selection, cost, and auto-detection. However, without annotations or output schema, it doesn't describe what the tool returns (image URLs? file paths? metadata?) or potential limitations. Given the complexity, it's mostly complete but missing output information.

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

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

Schema description coverage is 100%, so the schema already documents all parameters thoroughly. The description adds minimal value beyond the schema - it mentions 'auto-detection' logic which relates to the 'usePro' parameter, but doesn't provide additional semantic context about parameter interactions or usage patterns. The baseline of 3 is appropriate when the schema does the heavy lifting.

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

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

The description clearly states the tool's purpose: 'Generate images using Nano Banana (Gemini's native image generation).' It specifies the exact action (generate images) and resource (Nano Banana/Gemini), distinguishing it from sibling tools like gemini (likely text generation) and gemini-video-generate (video generation). The description immediately establishes this is an image generation tool with specific model options.

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 explicit guidance on when to use different model options: 'Fast, cheap (~$0.04/image), good for most use cases' for the default model versus 'Advanced model with better text rendering, infographics, diagrams' for Pro. It also explains auto-detection logic for Pro model usage and mentions the 'usePro' parameter for manual override. This gives clear decision criteria for model 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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool continues a conversation but lacks critical details: it doesn't mention whether this is a read-only or mutating operation (e.g., does it modify conversation history?), any authentication or rate limits, error handling (e.g., invalid conversationId), or the expected response format. For a tool with no annotations, this leaves significant gaps in understanding its 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 appropriately sized and front-loaded: the first sentence directly states the purpose, and the second sentence provides essential usage guidance. There is no wasted text, and both sentences earn their place by adding value beyond the tool name or schema.

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

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

Given the tool's moderate complexity (continuing a conversation with two required parameters), no annotations, and no output schema, the description is partially complete. It covers the basic purpose and usage context but lacks behavioral details (e.g., mutation effects, error handling) and output information. This makes it adequate as a minimum viable description but with clear gaps in 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 schema description coverage is 100%, with both parameters ('conversationId' and 'prompt') fully documented in the input schema. The description adds no additional semantic information beyond what the schema provides (e.g., it doesn't explain format constraints or examples). According to the rules, with high schema coverage (>80%), the baseline score is 3 even without param details in the description, which applies here.

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: 'Continue a Gemini conversation by providing the conversation ID and prompt.' This specifies the verb ('continue') and resource ('Gemini conversation'), making it distinct from its siblings like 'gemini' (likely to start a conversation) or media-specific tools. However, it doesn't explicitly differentiate from 'gemini-image' or 'gemini-video-check' in terms of conversation continuation versus media handling.

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 for when to use this tool: 'Use this to continue a multi-turn conversation started with the 'gemini' tool.' This explicitly links it to the sibling 'gemini' tool and indicates it's for follow-up interactions. However, it doesn't specify when not to use it (e.g., versus using 'gemini' for a new conversation or media tools for non-text inputs), which prevents a perfect score.

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

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

With no annotations provided, the description carries the full burden. It discloses key behavioral traits: it checks status, returns different data based on processing state, and can save files. However, it doesn't cover important aspects like error handling, rate limits, authentication needs, or what 'video data' specifically includes, leaving gaps for a mutation-adjacent 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 efficiently structured: a clear purpose statement followed by conditional outcomes, then parameter explanations. Every sentence adds value with no redundancy. The two-sentence parameter section is appropriately detailed without being 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 no output schema, the description is moderately complete. It covers the core functionality and parameters well but lacks details on return formats (what 'video data' entails), error cases, or system constraints. For a tool that interacts with potentially long-running operations, more behavioral context would be beneficial.

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

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

Schema description coverage is 100%, providing solid baseline documentation. The description adds valuable context: it clarifies that operationId is optional and defaults to 'last operation,' and explains the purpose of outputPath ('to save the video file when complete'). This enhances understanding beyond the schema's basic descriptions.

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

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

The description clearly states the tool's purpose: 'Check the status of a video generation operation' and specifies what it returns in different scenarios. It distinguishes from sibling tools by focusing on status checking rather than generation (gemini-video-generate) or other AI tasks, though it doesn't explicitly contrast with all siblings.

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

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

The description implies when to use this tool (after initiating video generation) by referencing 'operation ID from gemini-video-generate' and describing status checking behavior. However, it lacks explicit guidance on when to use alternatives or any exclusions, relying on contextual inference from the sibling tool reference.

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 and does well: it discloses the async nature ('starts an async video generation'), timing expectations ('takes 1-5 minutes'), return value ('Returns an operation ID'), and workflow dependencies (polling with gemini-video-check). It doesn't mention rate limits or authentication needs, but covers key behavioral aspects.

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

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

The description is well-structured and front-loaded: first sentence states core purpose, followed by timing/return info, then parameter list, then clear workflow steps. Every sentence earns its place with no redundant information. The bullet-point format for parameters and numbered steps for workflow enhance readability.

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

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

For a 4-parameter tool with no annotations and no output schema, the description does well: it explains the async behavior, return format (operation ID), and polling workflow. It could mention error handling or rate limits, but covers the essential context for proper tool invocation given the complexity.

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

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

Schema description coverage is 100%, so the baseline is 3. The description adds minimal value beyond the schema: it repeats parameter names and basic purposes but doesn't provide additional context about prompt best practices, aspect ratio implications, or resolution limitations. The 'from gemini-image' note for firstFrameBase64 is helpful but limited.

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 action ('Generate a video using Veo 3.1') and resource ('video'), distinguishing it from sibling tools like gemini-image (image generation) and gemini-video-check (polling). It explicitly identifies the model being used and the type of output.

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

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

The description provides explicit workflow guidance: 'Call gemini-video-generate → returns operationId', 'Wait 30-60 seconds', then 'Call gemini-video-check with operationId'. It names the specific alternative tool (gemini-video-check) for completion checking and explains the async nature of the operation.

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