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

The description adds valuable context beyond annotations: it explains session management behavior (starting vs. continuing conversations) and hints at statefulness. Annotations cover safety (readOnlyHint=false, destructiveHint=false, openWorldHint=true), so the bar is lower, but the description provides operational insights that enhance understanding of how the tool behaves in practice.

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 and front-loaded, consisting of just two sentences that efficiently convey the core functionality and key usage rule. Every sentence earns its place by addressing essential aspects without any wasted words.

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

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

Given the tool's complexity (multi-turn conversation with session management), rich annotations, 100% schema coverage, and the presence of an output schema, the description is complete enough. It focuses on the unique behavioral aspects (session management) while relying on structured fields for parameter and output details.

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

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

Schema description coverage is 100%, so the schema fully documents all parameters. The description adds minimal parameter semantics by clarifying sessionId usage, but it doesn't provide additional meaning beyond what's in the schema descriptions. This meets the baseline for high schema coverage.

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

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

The description clearly states the tool's purpose as 'Multi-turn conversation with session management,' which is a specific verb+resource combination. It distinguishes this tool from sibling tools like code_execution or generate_text by emphasizing conversation continuity rather than single-turn generation or 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?

The description provides explicit guidance on when to use this tool: 'Omit sessionId to start a new session; include it to continue an existing one.' This directly addresses the key decision point for usage versus alternatives, offering clear context for session management without needing 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?

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=true, covering safety and scope. The description adds valuable context about the sandboxed environment and that Gemini both generates and runs the code, which clarifies the execution flow beyond what annotations provide.

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 two sentences that efficiently convey the core functionality and agent role without unnecessary details. It's front-loaded with the main purpose and wastes no words, making it easy to parse quickly.

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 good annotations (covering safety and scope) and full schema coverage, the description adds useful context about the sandbox and Gemini's role. However, without an output schema, it could benefit from mentioning return values (e.g., code and results format), though it's not strictly required.

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 parameters are fully documented in the schema. The description doesn't add any parameter-specific details beyond what the schema provides, such as explaining the prompt format or model differences. Baseline 3 is appropriate given the high schema coverage.

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

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

The description clearly states the specific action ('Execute Python code'), target resource ('in a sandboxed environment'), and agent role ('Gemini generates and runs code'). It distinguishes from sibling tools like chat or generate_text by focusing on code execution rather than conversation or text generation.

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 Python code execution tasks but doesn't explicitly state when to use this tool versus alternatives like generate_text for non-code tasks or edit_image for image editing. No exclusions or specific contexts are provided beyond the general purpose.

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 indicate read-only, open-world, and non-destructive operations, which the description doesn't contradict. The description adds context about the editing process ('using a text prompt') and input requirements, but doesn't disclose behavioral traits like rate limits, authentication needs, or output format details beyond what annotations provide.

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

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

The description is a single, efficient sentence that front-loads the core purpose ('Edit an image using a text prompt') and specifies key inputs without unnecessary details. Every word earns its place, making it easy to parse quickly.

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 (6 parameters, image editing functionality) and lack of an output schema, the description is minimally adequate. It covers the basic operation but doesn't address output format (e.g., returned image type), error conditions, or advanced usage scenarios, leaving gaps for an AI agent to infer.

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 100% schema description coverage, the schema fully documents all 6 parameters. The description mentions 'base64-encoded image' and 'text prompt', aligning with the 'image' and 'prompt' parameters, but adds no additional semantic meaning beyond what's in the schema (e.g., how prompts are interpreted or image processing details).

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

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

The description clearly states the action ('Edit an image') and the mechanism ('using a text prompt'), specifying the required inputs (base64-encoded image and description). It distinguishes from sibling tools like 'generate_image' (creation vs. editing) but doesn't explicitly differentiate from 'edit_image_multi' beyond the single-image focus implied by the parameters.

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 editing existing images with text prompts, contrasting with 'generate_image' for creation from scratch. However, it lacks explicit guidance on when to choose this over 'edit_image_multi' (e.g., for single vs. multiple images) or other alternatives, and doesn't mention prerequisites like image format compatibility.

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 already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=true, covering safety and scope. The description adds minimal behavioral context: it mentions the AI model ('gemini-3-pro-image-preview') and the 14-image limit, which are useful but not comprehensive. It doesn't describe output format, latency, rate limits, or quality expectations. With annotations providing core safety info, the description adds some value but lacks rich behavioral disclosure.

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) and front-loaded with the core purpose. Every sentence adds information: the first states the function and constraint, the second names the AI model. There's no fluff or repetition. However, it could be more structured (e.g., separating function from technical details) and slightly more informative without losing conciseness.

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 (image editing with multiple references), the description is minimally adequate. Annotations cover safety and scope, and the schema fully documents inputs. However, with no output schema, the description doesn't explain return values (e.g., image format, errors). It also lacks context about the AI model's capabilities/limitations. For a creative tool with potential variability, more guidance 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?

Schema description coverage is 100%, so the schema fully documents all 4 parameters. The description adds no parameter-specific semantics beyond what's in the schema—it doesn't explain how 'prompt' interacts with 'images', what 'edit vs. compose' means for parameters, or provide examples. Baseline 3 is appropriate when the schema does all the parameter documentation work.

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

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

The description clearly states the tool's purpose: 'Edit or compose images using multiple reference images (up to 14).' It specifies the verb ('Edit or compose'), resource ('images'), and key constraint ('multiple reference images'). However, it doesn't explicitly distinguish this from its sibling 'edit_image' tool, which likely handles single-reference edits. The mention of 'gemini-3-pro-image-preview (Nano Banana Pro)' adds implementation detail but doesn't clarify functional differentiation.

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

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

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention the sibling 'edit_image' tool (for single-reference edits), 'generate_image' (for generation without references), or other image-related tools. There's no context about use cases, prerequisites, or exclusions. The only implicit guidance is the 'multi-reference' aspect, but this isn't framed as a decision criterion.

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 already declare readOnlyHint=true, openWorldHint=true, and destructiveHint=false, covering safety and scope. The description adds minimal behavioral context by specifying 'Gemini image models' and a default model, but doesn't disclose rate limits, authentication needs, output format (e.g., image type), or cost implications. With annotations providing core behavioral traits, the description adds some value but lacks depth.

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

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

The description is a single, efficient sentence with zero wasted words. It front-loads the core purpose and includes relevant technical details (Gemini models, default model) without redundancy. Every element earns its place, making it highly concise 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 tool's moderate complexity (image generation with 4 parameters), rich annotations (covering safety and scope), and 100% schema coverage, the description is adequate but incomplete. It lacks output details (no output schema), doesn't explain sibling relationships, and omits behavioral nuances like rate limits. However, annotations and schema compensate significantly, making it minimally viable for basic use.

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

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

Schema description coverage is 100%, with all parameters well-documented in the schema itself (e.g., prompt description, model enum with default, aspect ratio options, image size options). The description only mentions the default model ('Nano Banana Pro by default'), which partially overlaps with schema info. It adds negligible semantic value beyond the schema, meeting the baseline for high 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 tool's purpose: 'Generate an image from a text prompt using Gemini image models.' It specifies the verb ('Generate'), resource ('image'), and technology ('Gemini image models'), but doesn't explicitly differentiate from sibling tools like 'edit_image' or 'generate_text' beyond mentioning image generation. The default model mention adds specificity but doesn't fully address sibling differentiation.

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

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

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention sibling tools like 'edit_image' (for modifying existing images) or 'generate_text' (for text generation), nor does it specify use cases, prerequisites, or exclusions. The agent must infer usage 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?

Annotations already declare readOnlyHint=true, openWorldHint=true, and destructiveHint=false, covering safety and scope. The description adds minimal behavioral context beyond annotations - it mentions 'configurable model, temperature, and system instructions' which hints at customization options, but doesn't describe rate limits, authentication needs, response format, or error 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 a single, efficient sentence that front-loads the core purpose. Every word earns its place - 'Generate text' establishes the action, 'using Google Gemini models' specifies the technology, and 'with configurable model, temperature, and system instructions' highlights key customization options without unnecessary elaboration.

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 text generation tool with comprehensive annotations and 100% schema coverage but no output schema, the description is minimally adequate. It covers the basic purpose and hints at configurability, but doesn't address when to use it versus siblings, expected response format, or practical considerations for using Gemini models effectively.

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 100% schema description coverage, all parameters are well-documented in the schema itself. The description mentions 'configurable model, temperature, and system instructions' which maps to three of the five parameters, but doesn't add meaningful semantic context beyond what the schema already provides. The baseline of 3 is appropriate given the comprehensive schema coverage.

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

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

The description clearly states the verb ('Generate text') and resource ('using Google Gemini models'), specifying the core functionality. It distinguishes from some siblings like 'generate_image' or 'edit_image' by focusing on text generation, but doesn't explicitly differentiate from 'chat' which might also involve text generation with similar models.

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 like 'chat' or 'generate_with_search'. It mentions configurable parameters but doesn't indicate appropriate contexts, prerequisites, or exclusions for using this text generation 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?

Annotations already declare readOnlyHint=true, openWorldHint=true, and destructiveHint=false, covering the safety and scope profile. The description adds useful context about search grounding and citation behavior, but doesn't elaborate on rate limits, authentication needs, or what specific search results are used. With annotations providing core behavioral traits, the description adds moderate value.

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

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

The description is a single, efficient sentence that front-loads the core purpose. Every word earns its place: 'Generate text' establishes the action, 'with Google Search grounding' specifies the method, and 'for up-to-date, cited responses' explains the value proposition. There's zero waste or 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 tool's moderate complexity (search-augmented generation) and rich annotations covering safety and scope, the description is reasonably complete. It explains the search grounding and citation aspects well. The main gap is the lack of output schema, but the description doesn't need to explain return values. It could benefit from more detail about search behavior or limitations.

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

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

Schema description coverage is 100%, so all parameters are well-documented in the schema itself. The description doesn't add any parameter-specific information beyond what's in the schema. According to scoring rules, when schema coverage is high (>80%), the baseline is 3 even without parameter details in the description.

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

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

The description clearly states the tool's purpose with specific verbs ('Generate text') and resources ('with Google Search grounding'), distinguishing it from siblings like generate_text by emphasizing search-based, cited responses. It explicitly mentions the key differentiator of providing 'up-to-date, cited responses' which sets it apart from basic text generation 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 provides clear context for when to use this tool ('for up-to-date, cited responses'), implying it should be used when current information or citations are needed. However, it doesn't explicitly state when NOT to use it or name specific alternatives among the sibling tools, though the context suggests it's preferred over generate_text for factual queries.

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