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

With no annotations provided, the description carries full behavioral burden and does so excellently. It discloses output modality, the default model, the server-side max_tokens allocation behavior, the Gemini 3 thinking-token pitfall that can mimic a timeout, and a recommended timeout value. This is genuine transparency beyond what the schema provides.

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 front-loaded with purpose, then provides output modality, model default, a critical warning, and a timeout recommendation in only four sentences. Every sentence earns its place; there is no filler 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?

For a 5-parameter tool with a 100% documented schema and an output schema, the description is complete enough. It covers what the tool does, what it returns, the default model, the critical max_tokens constraint, and timeout expectations. The structured schema and output schema handle parameter details and return values, so the description does not need to repeat them.

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 100% with detailed per-parameter descriptions, so the baseline is 3. The description adds value by explicitly warning against setting max_tokens and explaining why ('a small cap is spent on Gemini 3 thinking and returns empty output that looks like a timeout'), plus pointing out the default model. This elevates it above the schema-only baseline.

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 opens with a specific verb and resource: 'Analyze and extract information from one or more images using Gemini multimodal understanding.' It also clarifies the output type ('Returns a text analysis - no image is generated'), which distinguishes it from image-generation siblings like generate_image. This is a clear, non-tautological statement of purpose.

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 clear use context: analyze/extract information from images and produce text output, not an image. It also provides critical operational guidance such as omitting max_tokens, the default model, and a recommended timeout. However, it does not explicitly name alternative tools like describe_image or state when NOT to use this tool versus those siblings, so it falls just short of a 5.

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 explicitly states the output is text and that no image is generated, and mentions the default model. The timeout recommendation is also included. However, it does not mention potential side effects, rate limits, cost implications, or any details about how the images are processed besides the model hint. This is adequate but not rich.

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 compact — two sentences plus a timeout recommendation. The core purpose is front-loaded: 'Analyze and describe...' The rest is supplementary. Every part adds value: the output type, the no-generation assurance, and the default model. No fluff 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 (4 params, nested images object, output schema present), the description covers the essential purpose, output, and default model. The schema handles parameter details, and the output schema clarifies return values. The timeout hint is a plus. However, it doesn't differentiate from the similar analyze_image sibling, which might be a slight gap. Overall, it's sufficiently complete for a description-focused 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 100% — every parameter (model, images, prompt, global_media_resolution) is well-described in the schema, including sub-fields like filePath, mimeType, and mediaResolution. The description itself adds minimal parameter info beyond the schema, but since the schema covers everything, the baseline of 3 applies. The description does note the default model, which matches the schema's instructions.

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: 'Analyze and describe one or more images' using Gemini models, and specifies the output: 'Returns a text description'. It also explicitly notes that no image is generated, which differentiates it from generation tools like generate_image. The verb+resource+output is specific and 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?

The description provides clear context on what the tool does (describes images, returns text) and implicitly indicates it's for description rather than generation. However, it does not explicitly mention when to use this over alternatives like analyze_image or when not to use it. The 'no image is generated' hint suggests it's not for image generation, but no explicit alternatives or exclusions 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?

The description discloses that the tool returns an edited image with preview and saves to disk, and mentions the underlying model family. However, it omits details such as token costs, whether the original is altered, or any side effects beyond saving. With no annotations, these gaps leave the description only partially transparent.

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

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

Two concise sentences, front-loaded with purpose. Every word contributes, no redundancy or unnecessary detail.

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 six parameters and no output schema, the description adequately covers the core workflow. It mentions return and disk saving, but does not elaborate on cost or how to choose between filePath and data for large images (though the schema covers that). Overall, it is reasonably complete for a typical use case.

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 full (100%) coverage and detailed descriptions for every parameter, including resolution options and thoughtSignature. The tool description itself adds no new information about parameters beyond what the schema already states, so a baseline 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?

The description clearly states the tool edits images using Google Gemini image models (Nano Banana Pro), explicitly distinguishing it from generation tools. It also notes the return of an edited image with preview and disk saving, making its purpose 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?

The description instructs to provide images and natural-language instructions, which implies the primary use case. It does not explicitly compare with alternatives like generate_image or mention when not to use it, but the context is clear.

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

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

No annotations are provided, so the description carries the full burden. It discloses critical behavioral traits: grounding by default, the max_tokens cap behavior (not consumption), the fact that values below 4096 are ignored, and that temperature is ignored on Gemini 3+ (forced to 1.0). It also explains the thinking_level parameter's scope and defaults. This is exemplary transparency for a complex 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 front-loaded with the core purpose and then dives into critical warnings. It is dense but not bloated; every sentence adds value. The only minor issue is that the max_tokens warning is repeated in both the description and the schema parameter description, which is slightly redundant but reinforces the critical point. Overall, it's well-structured 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 complexity (7 parameters, 1 required, 100% schema coverage, output schema present), the description is remarkably complete. It covers model selection, grounding, token budget behavior, temperature quirks, thinking levels, and timeout recommendations. The output schema exists, so return values don't need explanation. This is a model example of a complete tool description.

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%, but the description adds significant value beyond the schema. For max_tokens, it explains the cap-vs-consumption distinction, the 4096 threshold, and clamping behavior. For temperature, it notes the forced 1.0 on Gemini 3+. For thinking_level, it clarifies which models support which values. The description enriches every parameter with practical context.

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

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

The description clearly states the tool's purpose: 'Chat with Google Gemini models.' It specifies the default model (gemini-3.1-pro-preview) and grounding behavior, distinguishing it from sibling tools like gemini_deep_research or gemini_prompt_assistant. The verb 'chat' plus the resource 'Google Gemini models' is specific and 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?

The description provides explicit usage guidance: it warns against setting max_tokens, explains the server's automatic allocation, and clarifies that small values cause thinking tokens to burn the budget and return empty output. It also includes a recommended timeout (300000 ms) and the schema details valid model options and exclusions (e.g., 'Do NOT pass gemini-1.5-* or gemini-pro'). This is comprehensive and actionable.

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 of explaining behavior. It discloses that the tool performs multiple searches, synthesizes reports, and takes several minutes, including a recommended timeout. This is solid transparency for common behavioral concerns, even if it does not mention output format or potential failure modes.

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 and front-loads the core purpose and approach. Every sentence adds value, and the recommended timeout is embedded in a compact, parseable tag rather than verbose prose.

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?

This is a complex tool with an output schema, and the description covers the key behavioral side: iterative searches, report synthesis, and time requirement. It could say a bit more about what types of comprehensive reports are produced, but the output schema likely covers return-shape expectations.

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 provides 100% description coverage for all four parameters, so the baseline is 3. The description does not add extra parameter-level detail beyond what the schema supplies, but it reinforces that research_question should be complex and that the process is iterative.

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 identifies the tool as conducting deep research on complex topics with iterative multi-step analysis, which uses a specific verb and resource. This distinguishes it from sibling tools like gemini_chat and gemini_prompt_assistant by emphasizing multiple searches and comprehensive research reports.

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: complex topics requiring deep research, multiple searches, and comprehensive reports. It does not explicitly name alternatives for simpler queries, but the emphasis on complex topics and multi-step iteration makes the intended use case reasonably clear.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. The description is generic, saying 'Get comprehensive help' but does not specify what the tool returns (e.g., text output, how it behaves when topic is invalid, whether it requires network access). It doesn't disclose any potential side effects or limitations, leaving the agent with minimal 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 one concise sentence that clearly states the tool's purpose. It is front-loaded with the main verb 'Get' and includes the resource 'Gemini MCP' and the key aspects it covers, making it efficient and to the point.

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 help tool with a simple schema and no output schema, the description is adequate but not outstanding. It tells the agent what the tool does but does not explain what a help response looks like, how the topic parameter affects the output, or provide any usage examples. The tool has 12 siblings, so a bit more context on which topics are most commonly needed could help, but the current description is minimally 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 describes the single parameter 'topic' with an enum of valid values and a default of 'overview', providing full coverage (100%). The description does not add additional meaning beyond the schema, but with 100% coverage, the baseline of 3 is appropriate. The description's mention of 'features, settings, and best practices' may hint at the content of the topics, but it's not explicit.

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 provides comprehensive help about Gemini MCP features, settings, and best practices. It distinguishes it from sibling tools that perform specific actions like chat or image generation, making the purpose evident.

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 use when users need help or information about the Gemini MCP suite, but it doesn't explicitly state when not to use it or compare to alternatives. Sibling tools handle specific tasks, so the need for guidance is there, but the purpose is clear enough that an agent might infer when to use it.

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

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

With no annotations provided, the description carries the full burden of disclosing behavioral traits. It simply states the tool lists models without mentioning return format, pagination, or whether it's read-only. For a simple list operation, this is a significant gap, though the operation is inherently safe.

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

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

The description is a single, concise sentence that directly states the tool's function without fluff. It's 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?

For a simple list tool with no parameters and an output schema (not shown), the description adequately covers the core functionality. It doesn't elaborate on usage context, but given the simplicity, it's 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 tool has zero parametersтное schema is empty, so the description doesn't need to add parameter meaning. Baseline for 0 params is 4; the description correctly omits any param 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 'List available Gemini models and their descriptions' clearly states the tool's function with a specific verb ('list') and resource ('Gemini models'). It unambiguously distinguishes this tool from sibling tools like gemini_chat or gemini_prompt_assistant, which perform actions rather than enumeration.

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. While its purpose is self-evident, it lacks any explicit context or exclusions, such as whether it should be used before invoking chat tools or whether it lists all models or only certain ones.

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 clearly frames the tool as advice-giver ('Get expert prompt templates and guidance'), implying a read-only, non-destructive assistant. It does not disclose any hidden side effects or special behaviors, but for a guidance tool, this is minimal risk. No contradictions with annotations exist since none are present.

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, tightly packed with useful information. It front-loads the primary purpose, lists covered domains, and ends with a targeted usage note. Every sentence earns its place; no fluff 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?

With 7 parameters (5 enums) and no output schema, the description covers the core functionality and highlights the chart_design+color_scheme combination. It doesn't elaborate on every request_type, but the enum in the schema provides that list, and the description gives sufficient context for the most common branching scenario. It could mention that it also handles prompt optimization/troubleshooting, but the schema implies it via the request_type enum.

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 100%, so baseline is 3. The description adds a valuable cross-parameter hint: combining chart_design (request_type) with color_scheme yields a professional design system prompt. This enriches understanding beyond the schema's isolated parameter descriptions. It does not explain each parameter in depth, but the schema already does that adequately.

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 provides 'expert prompt templates and guidance for Gemini image generation' and lists specific areas (photography, charts, lighting, etc.). It distinguishes itself from siblings like generate_image by focusing on guidance rather than generation, and explicitly mentions chart_design for chart-specific needs.

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 an explicit usage hint for charts: 'For charts: use chart_design with a color_scheme to get a full professional design system prompt.' It doesn't enumerate when not to use it or list alternatives, but this guidance covers a key use case. Context for other request types is implied through the enum in the schema.

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 key behaviors: returns inline preview in Claude Desktop, saves full-resolution to disk, and mentions the default model. It also explains the use_search grounding behavior. However, it does not mention potential side effects like file overwriting, cost implications, or rate limits, which would 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?

The description is concise: two sentences that state the core function, the model family, the output behavior, and the default model. It is front-loaded with the primary action and avoids unnecessary fluff. Every sentence 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 the tool's complexity (8 parameters, no output schema, no annotations), the description is fairly complete. It covers the main purpose, default model, output behavior, and search grounding. However, it could mention that the tool can also edit images when provided with reference images (as implied by the images parameter and thoughtSignature), which would help agents understand its dual generation/editing capability.

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. The description adds value by explaining the default model and the use_search use cases (weather, current events, etc.). It also clarifies the global_media_resolution cost trade-offs, which is beyond the schema. However, it doesn't elaborate on the thoughtSignature parameter's role in conversational editing, which is partially covered in 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's purpose: 'Generate an image using Google Gemini image models (Nano Banana Pro).' It specifies the action (generate), the resource (image), and the technology (Gemini image models). It also distinguishes from siblings like edit_image, generate_svg, and generate_video by focusing on image generation with Gemini.

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 on when to use the tool (for generating images with Gemini) and mentions the default model. It also hints at usage for data-driven generation via use_search. However, it does not explicitly state when NOT to use it or mention alternatives like edit_image for editing existing images, which would be a stronger guideline.

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?

Since no annotations are provided, the description carries the full behavioral burden. It discloses that the output is an inline preview with responsive viewport controls, that the HTML has no external dependencies, and it includes a recommended timeout of 300000 ms. It doesn't cover side effects of saving a file or model differences, but the core behavior is well communicated.

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 only three sentences plus a timeout metadata tag. Each sentence earns its place: purpose, preview behavior, and the no-dependency constraint. It is front-loaded with the core action. The timeout metadata feels slightly out-of-place but is useful for the agent.

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 7-parameter tool with no output schema, the description provides the most critical context: an HTML landing page is generated, a preview is returned, and no external dependencies are used. The inline preview covers the return behavior. It does not explain what outputPath does in detail, but the schema covers that parameter. Overall it is sufficiently complete for the agent to invoke successfully.

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 already describes 100% of parameters, so the description does not need to add much parameter-level detail. The parameter descriptions cover meanings and defaults. The tool description itself doesn't add significant parameter semantics beyond the schema, so a baseline 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?

The description clearly states the tool generates a complete, self-contained HTML landing page via Gemini. This is a specific verb and resource, and it distinguishes from sibling tools like generate_image, generate_svg, and generate_video. The addition of inline preview and responsive viewport controls further clarifies the output format.

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: use this to create a self-contained HTML landing page and preview it in the IDE. It doesn't explicitly name alternatives or state when-not-to-use, but the purpose is unambiguous enough for an agent to choose this over sibling generation tools. The dependency-free constraint also helps narrow expectations.

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 transparency burden. It mentions the inline preview and a recommended timeout, which gives operational insight. However, it does not disclose side effects like file writing when outputPath is provided, whether the operation is read-only, or any permission requirements. The generative nature implies creation, but this is not explicitly stated.

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 plus a timeout note, with the primary action stated upfront. Every sentence adds value: the first defines purpose, the second describes output and preview, and the timeout note is practical. No filler 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 complexity (6 parameters, no annotations, no output schema), the description is fairly complete. It covers what it generates, the output format, and a timeout recommendation. However, it omits details like error handling, whether outputPath is required for saving, and how to specify style constraints beyond schema enums. These gaps are minor for a generation tool but prevent a higher score.

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 100%, so parameter descriptions already exist. The tool description adds contextual value by naming the types of graphics (diagrams, icons, etc.) but does not elaborate on parameter usage beyond what the schema provides. It meets the baseline for full schema coverage without adding significant new meaning.

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

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

The description clearly states the tool generates SVG graphics via Gemini, listing specific use cases (diagrams, illustrations, icons, data visualizations). This distinguishes it from sibling tools like generate_image (which likely produces raster images) and edit_image (which modifies existing images), making the purpose specific and 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?

The description implies usage for vector graphic creation but does not explicitly state when to prefer this over alternatives such as generate_image or when not to use it. It provides context (SVG, data visualization) but lacks direct guidance on tool selection or exclusion criteria.

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

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

With no annotations provided, the description carries the full burden. It discloses the async nature, processing time, and that it polls automatically, as well as dependencies like ffmpeg for thumbnails. It also implies mutations (creating files) but without explicit warnings, but this is covered by the nature of generation. It adds value beyond the schema by explaining behavior like automatic polling.

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 relatively compact for a complex tool, with key information front-loaded (model, duration, inputs, audio), followed by a warning about async processing. It uses bullet points effectively. It could be more concise, but for the complexity it is well-structured and not 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 high schema coverage and descriptive schema (nested objects, enums, bounds), the description completes the picture by explaining output artifacts (file path, thumbnail, HTML player) and processing time. It does not explain return structure, but there's no output schema, and the description hints at what is returned. For a generation tool with no output schema, this is 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 already has 100% coverage with detailed descriptions for each parameter, including example prompts, resolution trade-offs, and image input alternatives. The description reinforces the overall purpose but does not add additional parameter-level semantics beyond what's in the schema. Since coverage is high, a baseline of 3 is appropriate, but the description's mention of output paths and thumbnail/HTML player adds slight context, hence 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 that it generates videos using Google Veo 3.1, with specific details on duration, input types (text prompt, first-frame image, reference images), audio generation, and output artifacts (video file, thumbnail, HTML player). It distinguishes it from sibling image tools by emphasizing video generation and asynchronous processing.

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 explains key usage context: asynchronous with 2-5 minute processing time, automatic polling, and supports optional inputs like first-frame and reference images. It does not explicitly mention when NOT to use it or alternatives, but the context is clear enough for an agent to decide, especially with sibling tools like generate_image.

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?

Since no annotations are provided, the description carries the full behavioral burden; it discloses the base64 return format and supported image types, which are useful facts. However, it doesn't mention error behavior, file size limits, or security/permission considerations, so transparency is adequate but not comprehensive.

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

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

Two sentences efficiently deliver the essential information: reads a local image, returns base64, names its consumers, and lists supported formats. There is no filler or redundant repetition of the 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?

For a single-parameter tool with an output schema, the description covers the key behavioral context: input, output, and supported formats. It could mention potential failure conditions, but these are not critical for a defensive agent's selection and invocation of such a straightforward tool.

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

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

The schema already fully describes filePath, so the baseline is 3. The description supplements it by emphasizing 'local image file' and listing supported formats, which adds mildly relevant context 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 action ('Read a local image file') and the resource being handled, with an explicit output type. It also differentiates itself from sibling tools by explaining the result is ready to feed into generate_image, edit_image, describe_image, or analyze_image.

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

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

The description explicitly names the downstream tools that accept its output, giving strong context for when to use this tool. It doesn't state an explicit 'do not use when' condition, but for a focused loading utility, this is a minor gap.

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