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

Without annotations, the description carries the burden. It discloses key traits: returns text only, default model, and multimodal understanding. However, it omits details like error handling, size limits, or idempotency.

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

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

Two sentences, no wasted words. Front-loaded with the core purpose, followed by a key behavioral note and default model. Highly 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 5 parameters, an output schema, and no annotations, the description covers the essential purpose and a behavioral trait. It lacks sibling differentiation and usage context, but otherwise meets needs for a moderately complex 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?

Input schema coverage is 100% with detailed descriptions for all parameters. The tool description adds minimal extra meaning beyond restating the default model, so baseline 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 clearly states the tool analyzes and extracts information from images and returns text. It distinguishes from image generation tools by stating 'no image is generated,' but does not explicitly differentiate from similar analysis tools like describe_image or extract_structured_data.

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

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

No guidance on when to use this tool versus alternatives. The description does not mention scenarios or limitations, leaving the agent to infer usage without explicit directions.

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 a text description and does not generate images, but it does not mention other behavioral traits such as read-only nature, authentication needs, or rate limits. With no annotations, this is a moderate 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 concise (two sentences) and front-loaded with the primary action. Every sentence serves a purpose: stating the action and model, clarifying output, and specifying the default model.

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 straightforward image description tool, the description covers the essential purpose and output. However, with many siblings, more context on differentiation could improve completeness. The presence of an output schema reduces the need for return value 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 baseline is 3. The description itself does not elaborate on parameters; all parameter details are already in the schema. No additional meaning is added.

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') and resource ('images'). It specifies the method (Google Gemini image models) and explicitly notes that no image is generated, preventing confusion with generation tools. The default model is also mentioned, adding specificity.

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

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

No guidance is given on when to use this tool versus siblings like 'analyze_image' or 'extract_structured_data'. The description lacks context for appropriate usage scenarios or alternatives, leaving the agent without decision support.

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

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

With no annotations, the description carries the full burden. It mentions returning an inline preview and saving to disk, but does not disclose potential side effects or requirements like authentication. Adequate but not detailed.

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, clearly front-loaded with the core action. Every sentence adds value, though could be structured with bullet points for better 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 tool with 6 parameters and no output schema, the description partially addresses return values (inline preview, save to disk). However, it does not specify response structure or additional context like default save locations, leaving gaps.

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

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

Schema description coverage is 100%, so the schema provides detailed parameter meanings. The description adds no further parameter details beyond the schema, hence baseline score of 3.

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 Gemini models, with natural language instructions. It distinguishes itself from siblings like generate_image (creates) and analyze_image (analyzes).

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 images with natural language, but does not provide explicit when-to-use or when-not-to-use guidance. It lacks differentiation from similar tools like generate_image for image creation tasks.

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

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

With no annotations provided, the description must fully disclose behavior. It mentions 'Gemini JSON mode' and that it 'returns parsed JSON', but does not discuss error handling, file size limits, or permissions needed. The phrase 'almost any local file' is vague. There is no annotation contradiction.

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 two sentences, with the purpose and method in the first sentence and key parameters in the second. It is front-loaded and waste-free. However, it could be slightly more structured by separating the input types from the output.

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, wide input types) and the presence of an output schema (though not provided), the description covers the core functionality well: what it does, how to specify fields, and how to constrain output. It is complete enough for most use cases, though it does not detail the exact return format (referencing 'parsed JSON' is sufficient given output schema).

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?

All 6 parameters have descriptions in the input schema (100% coverage), so the description adds minimal extra meaning. It clarifies the purpose of 'instructions' and mentions that 'json_schema' can constrain output, but these points are already implied by the schema descriptions. Baseline 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 it extracts structured JSON from text or local files using Gemini JSON mode. It is specific about the verb 'extract' and the resource 'structured JSON', but does not explicitly differentiate from sibling tools like 'analyze_image' or 'ocr', which could also extract data from files. However, the scope is broad, and the description is unambiguous.

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

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

The description suggests using the tool when you need structured data from various file types, but it does not provide when-not-to-use or alternatives among siblings. The mention of 'optional' json_schema gives some guidance, but there is no explicit usage context 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, the description carries full burden. It discloses autonomous file editing, shell command execution, directory working, return of a conversation_id for continuation, auto_approve default, sandbox option, and timeout. It does not explicitly discuss destructive actions or permission requirements, but is largely 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 a single paragraph of six sentences, front-loaded with the primary action, followed by differentiation, usage context, return value, and model advice. Every sentence serves a purpose 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 complex tool with 9 parameters and an output schema, the description covers the core behavior, usage context, sibling differentiation, return value, and model selection advice. It is well-rounded and provides sufficient context for an agent to select and invoke the tool correctly.

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 does not add significant per-parameter meaning beyond the schema; it repeats the task parameter's instruction to be explicit and mentions model selection advice, but does not elaborate on other parameters.

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

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

The description clearly states the tool delegates a task to an autonomous Gemini agent that can read/edit files and run shell commands for multi-step work, returning a final report. It explicitly distinguishes from `gemini_chat`, a sibling tool that returns a single text response.

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 specifies that the tool is for 'self-contained coding/research/automation tasks' and contrasts with `gemini_chat`. It advises model selection (Flash for speed, Pro for reasoning) and refers to the sibling `gemini_agent_models` for exact labels, providing clear when-to-use and alternative guidance.

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

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

No annotations are provided, so the description carries full burden. It discloses that labels come from `agy models` and are agent-specific, which is useful. However, it does not mention any potential side effects, rate limits, or list ordering. For a simple listing tool, this is adequate.

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

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

Two sentences, no wasted words. The first sentence states the purpose, the second adds the critical distinction and usage hint. Efficiently front-loaded.

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

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

Given 0 parameters and an output schema, the description covers the tool's purpose, source, and differentiation from a sibling. It could briefly note that no arguments are needed, but that is inferable from the schema. Overall complete for a listing 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?

With 0 parameters, baseline is 4. The description adds meaning by specifying the output is model labels for the agent and that they should be used exactly as the 'model' parameter in the agent. This is beyond what the empty schema provides.

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 model labels for the Gemini agent, and distinguishes it from the sibling gemini_list_models by noting the source and purpose. The verb 'List' and resource 'model labels' are specific.

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

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

The description explicitly contrasts with gemini_list_models ('differ from the API models'), providing a clear when-to-use and when-not-to-use. It also instructs to use the exact label as the agent's model.

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

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

With no annotations, the description must disclose behaviors, but it only states the action. It does not mention that the tool mutates state (e.g., conversation history), requires authentication, has rate limits, or that some parameters like thinking_level are model-specific. The input schema covers defaults but not behavioral effects.

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

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

The description is a single sentence, which is concise and front-loaded. It opens with the key purpose. However, given the tool's complexity (7 parameters, output schema, many siblings), it may be too brief and omits useful context.

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

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

Despite the presence of an output schema, the description lacks context about how this tool fits into the broader toolset. It does not clarify when to prefer this over gemini_agent or gemini_prompt_assistant, and it omits details about conversation state, model selection behavior, or response structure.

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

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

Schema coverage is 100%, so the schema documents all parameters with type, descriptions, and defaults. The description adds no extra meaning beyond what the schema provides, hence 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 'Chat with Google Gemini models' clearly states the verb (chat) and resource (Gemini models). It distinguishes itself from sibling tools like gemini_deep_research or gemini_agent by focusing on conversational interaction, but does not explicitly differentiate from gemini_agent or gemini_prompt_assistant, which may overlap.

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

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

No guidance on when to use this tool versus alternatives like gemini_agent or gemini_deep_research. There is no mention of use cases, preconditions, or exclusions, leaving the agent without context for choosing among similar tools.

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?

Despite no annotations, the description discloses key behaviors: autonomous, multi-step live web search, synthesized cited report, takes several minutes, and includes a recommended timeout. This gives sufficient transparency for an AI agent.

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

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

The description is concise with two sentences, front-loading the purpose, and includes a valuable timeout hint. No unnecessary words.

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

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

For a complex tool with an output schema, the description provides good context: behavior and API usage. It could mention the exact output format but is largely 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 100%, so each parameter is already described in the schema. The description does not add significant extra meaning beyond what's in the schema fields. Baseline 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 it conducts 'real Deep Research' using Google's autonomous agent, distinguishing it from sibling tools like chat or image analysis. The verb 'conducts' and resource 'Deep Research' are specific and informative.

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 for complex topics requiring multi-step web search and takes minutes, but does not explicitly state when not to use or name alternatives. It provides clear context but lacks 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 exist, so the description carries the burden. It correctly indicates the tool returns help information and does not have side effects. While it could mention output format (e.g., textual), it is adequate for a simple read-only tool. No contradictions found.

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 front-loads the action and resource. It could be slightly more informative about the output, but it is not verbose and effectively communicates the core purpose.

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 one optional parameter, no output schema, and no annotations, the description covers the essential purpose and usage. An agent can infer how to use it from the parameter enum. It is complete enough for a help 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 input schema has full coverage (100%) with a description for the 'topic' parameter. The tool description does not add extra meaning beyond the schema. At baseline, a score of 3 is appropriate since the schema already serves the purpose.

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 help about Gemini MCP features, settings, and best practices. The verb 'get comprehensive help' and specific resource 'Gemini MCP' make the purpose unambiguous and distinct from sibling tools that perform tasks like image analysis or chat.

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 (ask for help on a topic), but no explicit guidance on when to use this tool versus alternatives. Given many sibling tools, the description would benefit from stating that it is for learning or reference rather than performing actions.

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

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

No annotations are provided, and the description only states the basic function without disclosing potential behaviors like authentication needs, caching, or pagination, though the tool is simple with no 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 a single, concise sentence that is front-loaded and easy to parse, with no wasted words.

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

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

Given the tool's simplicity (zero parameters, output schema present), the description is nearly complete, though it could provide a hint about the output structure or intended 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?

Schema coverage is 100% (no parameters), so baseline applies; the description adds no parameter information beyond what the schema already conveys.

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 ('List') and the resource ('available Gemini models and their descriptions'), distinguishing it from sibling tools that use models rather than list them.

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

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

No explicit guidance on when to use versus alternatives, but the tool's purpose is self-explanatory as a discovery tool; usage is implied.

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 describes the types of assistance offered but does not disclose limitations, side effects, or input validation behavior. The description adds some context but lacks depth on operational details.

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

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

The description is extremely concise with only two sentences plus a chart-specific hint. Every sentence adds unique value, and the structure is front-loaded with the core purpose, followed by scope and a specific usage tip.

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 7 parameters and no output schema, the description covers major use cases and provides a specific hint for chart design. It lacks detail on some request types like optimize_prompt or troubleshoot, but the schema fills those gaps. Overall, it is sufficiently complete for guiding an AI 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 100%, so the baseline is 3. The description adds extra semantics by explicitly linking chart_design request type with color_scheme and listing use cases that match the enum, providing guidance beyond the schema.

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

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

The description clearly states the tool's purpose: providing expert prompt templates and guidance for Gemini image generation, covering photography and chart design. It distinguishes itself from siblings like generate_image by focusing on prompting assistance rather than direct image 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 includes explicit guidance for using chart_design with a color_scheme for professional design system prompts, which helps in choosing the right request type. However, it does not provide when-not-to-use scenarios or compare with alternative tools.

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 output delivery (inline preview, save to disk) and default model, but with no annotations, it does not cover potential behavioral traits like rate limits, authentication needs, or the ability to handle reference images. It provides some useful context but is 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, front-loaded with the key action. Every sentence adds value: first states the core function, second adds output details. No wasted words.

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

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

Given the tool's complexity (8 parameters, 3 enums, no output schema), the description is too brief. It omits critical capabilities like reference images, search grounding, aspect ratio control, and the thoughtSignature editing feature. The user must rely entirely on the schema for understanding, which is inadequate for a high-level overview.

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 does not add any extra meaning beyond what the schema already provides for parameters. It does not mention any parameter details, so it neither harms nor significantly enhances understanding.

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 an image using specific models and mentions output behavior (inline preview, saving to disk). The verb 'generate' and resource 'image' are specific, and the tool name itself distinguishes from siblings like edit_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?

No guidance on when to use this tool over alternatives such as edit_image or generate_svg. The description does not provide any context about appropriate scenarios or exclusions.

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

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

With no annotations, the description provides key behavioral traits: returns inline preview, responsive viewport controls, no external dependencies, inline CSS and vanilla JS. This goes beyond merely saying 'generate' but lacks details about output handling (e.g., success/error) beyond mentioning optional outputPath.

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, front-loaded with the core action, and every word adds value. No redundancy or superfluous 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 7 parameters and no output schema, the description adequately communicates the output behavior. It could specify the exact return format (e.g., HTML string vs file) but overall covers key 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?

Schema coverage is 100%, so the baseline is 3. The description does not add significant parameter-level insights beyond what the schema already provides. The mention of 'inline preview' relates to output, not parameters.

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

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

The description uses a specific verb 'Generate' and identifies the resource as 'a complete, self-contained HTML landing page using Gemini'. It clearly distinguishes from sibling tools like generate_image or generate_svg by specifying the output type and constraints.

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 for generating landing pages, which is distinct from sibling tools. However, it does not explicitly state when not to use this tool or suggest alternatives, though the context of sibling tools makes the purpose 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?

With no annotations, the description effectively discloses key behavioral traits: supported file types, that file_path is loaded server-side (bypassing MCP limits). It does not mention idempotency, rate limits, or auth, but for a summarization tool these are less critical. The server-side loading detail adds 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 two sentences, front-loaded with the core purpose, and every word adds value. No extraneous information, 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 complexity (6 parameters, many file types), the description covers most key aspects: input options, length, focus, language. However, it does not clarify mutual exclusivity of text and file_path, nor file size limits. With an output schema present, return values need not be explained.

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

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

Schema coverage is 100%, but the description adds meaning beyond the schema by specifying the types of files accepted for file_path and noting server-side loading. This enhances the agent's understanding beyond basic parameter 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 explicitly states the tool summarizes text or local files with Gemini, listing supported file types. This clearly differentiates it from sibling tools like analyze_image or gemini_chat, which serve different purposes.

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 instructions on how to use the tool (provide text or file_path, choose length, optional focus/language) but does not explicitly state when to use this tool vs alternatives. It implies summarization tasks but lacks direct comparison with siblings like gemini_agent or chat.

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 mentions using Gemini and returning an inline preview, which provides moderate transparency. However, it omits details like network usage, authorization, or potential side effects.

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

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

The description is two sentences, front-loaded with purpose, and contains no redundant information.

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

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

For a tool with 6 parameters and no output schema, the description mentions the return type (inline preview with SVG viewer) and covers the basic purpose, but lacks details on output format and error handling.

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 description adds little beyond what the schema already provides. It does not elaborate on parameter formats or constraints.

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 specifies the tool generates SVG graphics using Gemini for multiple use cases like diagrams and icons, distinguishing it from siblings like generate_image (raster) and generate_landing_page.

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

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

The description states what the tool does but does not provide explicit guidance on when to use it versus alternatives like generate_image 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 provided, the description fully carries the behavioral transparency burden. It discloses the async processing, auto-polling, processing time estimates, and output features (file path, thumbnail, HTML player). No contradictions exist since annotations are absent.

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 structured into two clear paragraphs. It is concise but includes necessary warnings and details. Minor redundancy (e.g., mentioning processing time twice) could be trimmed, but overall efficient.

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

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

Given the tool's complexity (13 parameters, nested objects, no output schema), the description adequately covers inputs, behavior, and basic output format. However, it lacks explicit error handling details, failure modes, or return type schema, which would be beneficial for a complex async 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 coverage is 100%, so parameters are well-documented. The description adds value beyond the schema by summarizing key behaviors (e.g., resolution impact on time, audio generation, thumbnail extraction) and providing a concrete prompt example, which aids agent decision-making.

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 videos using Google Veo 3.1 AI model, specifying duration (4-8 seconds), input types (text prompts with optional images), and outputs (file path, thumbnail, HTML player). It distinguishes itself from siblings like generate_image (image generation) and transcribe (audio processing) by focusing on video creation.

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 guides usage by noting the async nature and 2-5 minute processing time, but it does not explicitly state when to use this tool versus alternatives like generate_image for static images or when not to use it (e.g., for editing existing videos). The warning and auto-polling note help manage 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?

No annotations are provided, so the description independently must cover behaviors. It mentions the return format and supported types but omits potential errors, file size limits, or path accessibility constraints.

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 (one sentence) and front-loaded with the main action, efficiently communicating key information without extraneous 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 simplicity (one parameter, no nested objects) and the existence of an output schema, the description adequately covers what the tool does and how its output is used.

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

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

The single parameter 'filePath' is fully described in the schema (100% coverage). The tool description adds no further detail about path semantics, such as relative base directory.

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 reads a local image file and returns base64-encoded data, listing specific compatible tools and supported formats. It distinguishes itself from sibling tools that consume such data.

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 indicates the tool is for loading local images before passing to other tools, but does not explicitly state when not to use it or mention alternatives.

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

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

No annotations provided, so the description carries full burden. It transparently states the tool uses Gemini multimodal OCR, returns raw text as Markdown, and does no summarising or analysis. It also mentions token cost implications for resolution.

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 consists of two concise sentences. The first sentence clearly states the purpose and verb, and the second provides a valuable tip. No unnecessary words.

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

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

Given the tool complexity (6 params, 1 required, output schema exists), the description covers the core purpose and a key performance tip. It doesn't explain all parameters, but the schema covers them adequately. Could mention handling multiple images, but not essential.

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 baseline is 3. The description adds marginal value beyond the schema, such as the tip about MEDIUM resolution and using filePath for large files. It does not compensate for any missing schema information.

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 extracts text verbatim from images or PDFs using Gemini multimodal OCR. It specifies the output as raw text in Markdown and explicitly notes no summarising or analysis, distinguishing it from sibling tools like analyze_image or extract_structured_data.

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 raw text extraction and provides a useful tip about MEDIUM resolution for documents/PDFs. However, it does not explicitly state when not to use this tool or mention alternatives among siblings.

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

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

No annotations are provided, so the description must carry the full burden. It does not disclose what happens to uploaded files, privacy implications, rate limits, or error behaviors (e.g., unsupported formats). The mention of 'using Gemini' implies cloud processing but lacks specifics.

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, front-loaded with the core purpose. Every phrase adds value: 'using Gemini' signals the engine, 'Optional timestamps...' summarizes key params. 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 (9 params, no required, output schema exists), the description covers key options and input methods. It could mention file size limits or performance notes, but is otherwise sufficient for standard transcription tasks.

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 baseline is 3. The description adds a high-level summary of optional features (timestamps, diarization, language hint) and input methods, but does not provide semantics beyond what the schema already offers.

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 'Transcribe speech from an audio or video file to text using Gemini.' It specifies the action (transcribe), resource (audio/video file), and model (Gemini), making the purpose immediately clear. No sibling tool does transcription, so differentiation is implicit.

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

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

No guidance on when to use this tool versus alternatives is provided. The description does not mention prerequisites, file size limits, or alternative tools (e.g., gemini_agent for custom prompts). The agent would lack context for tool selection.

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