Reelfy

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

The description adds useful behavioral context not present in annotations: cost per call (~$0.08) and return format (PNG URL(s)). Annotations already indicate a non-read-only, non-destructive operation, and the description does not contradict them, but it adds concrete 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 exceptionally concise: one sentence with three key facts (generate image, model, cost, return format). Every word earns its place, and the main action is 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?

For a simple two-parameter generation tool, the description is nearly complete: it names the model, price, and return format, and an output schema is present so return values are already structured. Minor gaps include lack of rate limits or content restrictions, but these are not critical given the tool's simplicity.

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 does not add any parameter-specific meaning beyond what the schema already provides (e.g., 'What to draw' and aspect ratio options).

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 function: 'Generate an AI image' with a specific verb and resource. It also names the model variant and differentiates from sibling tools like ai_music and ai_video.

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

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

Usage is implied by the name and purpose ('generate an AI image') but there is no explicit guidance on when to use it vs alternatives, nor any exclusions or conditions. It simply states the action, cost, and return format.

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

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

Annotations already indicate non-read-only, non-destructive, and open-world behavior. The description adds valuable context beyond annotations: the specific external model (Black Forest Labs), the photorealism focus, and the cost (~$0.08), which helps the agent anticipate side effects and the need for payment.

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, front-loaded sentence that conveys the core purpose, model, style, and cost without any wasted words. Every element earns its place.

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 2-parameter tool with an output schema, the description covers the essential context: what it does, which model, and costs. It does not mention latency or any prompt constraints, but the output schema and annotations handle return values and safety, so this is sufficient.

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

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

Schema description coverage is 100%: 'prompt' is described as 'What to draw' and 'aspect_ratio' lists all valid values with a default. The tool description adds no additional parameter semantics, 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?

The description clearly states the action ('Generate an AI image') and specifies the model (Flux 2) and provider (Black Forest Labs) with a distinctive style tag ('photorealism'). This distinguishes it from sibling tools like ai_image, ai_image_gpt, and ai_image_pro, which target different models or performance levels.

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

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

The description implies when to use this tool (when a photorealistic image is desired, specifically via Flux 2) and mentions a cost factor (~$0.08). However, it does not explicitly compare alternatives or state when not to use it, so it falls short of a full 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?

Annotations already indicate this is a non-read-only, non-destructive operation. The description adds valuable behavioral context: approximate cost (~$0.07) and output format (returns PNG URLs), which helps the agent set expectations about the result.

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 communicate the core purpose, cost, and output format with zero unnecessary detail. The information is front-loaded and easy to parse.

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 two-parameter tool with an output schema, the description covers the essentials: what it does, cost, and return type. It could mention any prerequisites (e.g., API key) or rate limits, but annotations address safety, so the description is sufficiently complete.

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

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

The input schema already documents both parameters with high coverage (100%). The prompt description adds a small nuance ('English works best'), but the aspect_ratio list is fully covered in the schema, and the description doesn't provide additional semantic meaning beyond structured fields.

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

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

The description clearly states the tool's purpose with a specific verb ('Generate') and resource ('AI image with OpenAI GPT Image 2'). It distinguishes from sibling image tools by naming the exact model (GPT Image 2), unlike ai_image_flux or ai_image_pro.

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?

There is no guidance on when to use this tool versus alternatives. The description doesn't reference any sibling tools or provide exclusion criteria, despite the context showing multiple related image 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?

Annotations already indicate this is not a read-only operation (readOnlyHint=false). The description adds valuable behavioral context beyond annotations by disclosing the output resolution (2K), the specific model (Nano Banana Pro), and the cost (~$0.18), which are important side-effect and resource-usage 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 a single, front-loaded sentence that captures the essential action, use case, and cost. Every phrase contributes value, with no redundancy or filler.

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 only two parameters, full schema coverage, and an output schema, the description is remarkably complete. It specifies the tool's purpose, its unique selling point, the output resolution, and the cost, leaving no significant gaps 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?

The input schema provides 100% coverage for both parameters: prompt ("What to draw") and aspect_ratio (with allowed values and default). The description adds no parameter-specific meaning, so it meets the baseline of 3 as defined when schema coverage is high.

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 function with a specific verb and resource: "Generate a hi-res 2K image". It also names the model (Nano Banana Pro) and highlights its differentiator ("best for text-in-image & infographics"), which distinguishes it from sibling image generation tools like ai_image, ai_image_flux, and ai_image_gpt.

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: it is positioned as the best option for text-in-image and infographics. It does not explicitly state when NOT to use it or name alternative tools, but the use-case guidance is strong enough for an agent to infer the appropriate scenario.

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

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

Annotations are present (readOnlyHint: false, destructiveHint: false), so the agent already knows it is a write operation. The description adds valuable behavioral context: cost ('~$0.15'), latency ('Takes 1-3 minutes'), and output specifics ('2 track variants + cover art'). It also names the model version (Suno V4.5), which helps set expectations. No contradiction with annotations.

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 that front-loads the primary action, then adds cost and time as separate concise clauses. Every word contributes value, with no redundancy or filler. It is highly scannable and appropriately sized.

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 low complexity (2 parameters, one required) and the presence of an output schema, the description covers the main operational aspects: what it generates, cost, and duration. It leaves out potential failure modes or usage restrictions, but these are not essential for basic invocation. The completeness is strong for a generation tool, though not exhaustive.

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 100% description coverage for both parameters, so the baseline is 3. The description itself does not add further semantic details about parameters like 'prompt' or 'instrumental'; it only refers to the overall song generation. Schema descriptions already explain the prompt and the 'true = no vocals' meaning for instrumental.

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 clearly identifies the resource: 'a full song with vocals (Suno V4.5)'. It also specifies the scope ('2 track variants + cover art') and distinguishes this tool from siblings like ai_image, ai_video, and ai_voice by focusing on music 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 does not provide explicit guidance on when to use this tool versus alternatives. It only states what it does, but there are no exclusions, prerequisites, or references to sibling tools like ai_voice or ai_image. The phrase 'full song' implies music generation, but it never says 'use this for generating songs' directly.

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

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

Annotations indicate a non-read-only, non-destructive operation. The description adds useful behavioral context: cost (~$0.50), duration (1-4 minutes), and format (8-second, native audio), which are not in the annotations.

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?

A single concise sentence that front-loads the main purpose and includes essential specifics. No wasted words.

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

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

For a 2-parameter tool with an output schema, the description covers purpose, key specs, cost, and runtime. It does not explain output format, but the output schema likely covers that.

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 3 applies. The description does not add extra parameter details beyond what the schema already 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?

Description states 'Generate an 8-second AI video clip' with specific details (native audio, Google Veo 3.1 Fast). This clearly distinguishes it from sibling tools like ai_image or ai_music.

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 context is clear: it generates video clips, which implies use when a video is needed. However, it does not explicitly mention when not to use it or name 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?

Annotations already indicate readOnlyHint=false and destructiveHint=false. The description adds useful behavioral context: fixed duration (5 seconds), lack of audio, expected cost, and processing time. This enriches the agent's understanding of the tool's behavior beyond the schema and annotations.

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, information-dense sentence containing the action, model, duration, audio status, cost, and processing time. Every word adds value 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 simple generation tool with 2 parameters and an output schema, the description covers key operational facts (length, audio, cost, latency). The only omission is differentiation from sibling video tools, but the core usage context is well addressed.

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 description does not need to explain parameters. The description mentions fixed output characteristics (5 seconds, no audio) but no additional meaning for 'prompt' or 'aspect_ratio' 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 generates a 5-second video using Kling 2.6 and specifies no audio. It distinguishes itself from sibling tools by naming the specific model, duration, and audio absence.

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 cost (~$0.60) and latency (1-3 minutes), which imply suitability for quick/cheap video generation, but it does not explicitly compare with alternatives like ai_video_seedance or ai_video. No exclusions or when-not-to-use guidance is 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?

Annotations already indicate a non-read-only, non-destructive operation. The description adds valuable context beyond annotations: the fixed duration (5 seconds), resolution (720p), lack of audio, speed, and price (~$0.35). No contradiction with annotations; this context helps set expectations for cost and latency.

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?

A single sentence that front-loads the core action and includes essential specs and cost. Every word adds value; there is no redundancy or filler.

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 an output schema present and only two simple parameters, the description covers the key behavioral and business aspects (what, specs, cost). No need to explain return values since the output schema exists. The tool definition is adequately complete for an agent to use it 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?

Input schema provides 100% coverage with descriptions for both parameters (prompt and aspect_ratio). The tool description adds no additional parameter-level detail, so the baseline of 3 is appropriate; the schema fully carries the semantic load.

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 states a specific verb ('Generate') with a resource ('5-second 720p video'), names the model (ByteDance Seedance 2.5), and clarifies key specs (no audio, fast & cheap). This clearly distinguishes it from sibling video tools like ai_video and ai_video_kling.

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

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

The description implies usage context ('fast & cheap') but does not explicitly state when to choose this tool over alternatives like ai_video_kling, nor does it provide exclusions for when not to use it. The 'no audio' and cost hints provide some guidance, but it falls short of explicit when/when-not instructions.

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 adds cost information (~$0.05) and the use of Claude, which provides behavioral context beyond the annotations (readOnlyHint=false, openWorldHint=true). However, it does not disclose potential side effects like data handling or response format details. With annotations present, this 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?

The description is a single sentence that front-loads the purpose, includes examples, and even mentions cost. Every word earns its place; 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?

The tool is simple with two parameters and an output schema exists, so return values are presumably covered. The description covers purpose, cost, and example uses. It could mention privacy or image handling, but for a tool of this complexity, the description 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% with descriptions for 'q' (What to do with the image) and 'image' (Public URL with format/max size). The description adds example tasks (OCR, chart reading) that hint at the use of 'q', but the schema already carries the parameter definitions. Baseline 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's function: 'Analyze an image with Claude' followed by specific use cases (OCR, chart reading, screenshot explanation). This provides a specific verb and resource, and differentiates it from sibling tools like ai_image or ai_music by focusing on image analysis.

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 image analysis tasks but does not explicitly state when to use this tool over alternatives. There is no mention of when not to use it, nor any reference to sibling tools, leaving guidance implied rather than explicit.

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

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

Annotations already indicate the tool is not read-only and may have side effects, but the description adds valuable behavioral context: it produces an MP3, specifies the underlying model, supports 32 languages, and has a 1000-character limit. It also discloses the approximate cost (~$0.05), which is useful for planning. No contradictions with annotations.

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, front-loaded sentence that packs essential information: output format, model, language count, character limit, and cost. Every word contributes value, with 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 simplicity (2 params, no nested objects) and the presence of an output schema and annotations, the description is largely complete. It covers model, output type, languages, length limit, and cost. Missing explicit guidance on when to choose this over sibling media tools, but that gap is minor for such a straightforward TTS 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 covers 100% of parameters (text and voice) with descriptions, so the baseline is 3. The description adds meaningful constraint for the text parameter ('up to 1000 chars'), which is not stated in the schema. This extra detail enhances parameter understanding beyond schema definitions.

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 'Text-to-speech voiceover MP3' clearly states the tool's function with a specific verb and output format, distinguishing it from sibling tools like ai_image and ai_music. It also provides concrete details (ElevenLabs Turbo 2.5, 32 languages, char limit) that reinforce the 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?

Usage is implied by the text-to-speech description, but there are no explicit statements about when to use this tool versus alternatives like ai_music or ai_video. The description doesn't mention exclusions or provide alternative tool references, so guidance remains indirect.

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 adds useful context beyond the annotations by mentioning the cost (~$0.03) and promising a 'concise answer'. However, it does not disclose other behavioral traits such as potential non-determinism, latency, or that the tool may consume credits. Annotations provide readOnlyHint=false and openWorldHint=true, but the description does not elaborate on these, so transparency is moderate.

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

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

The description is extremely concise and tight: one sentence covering purpose, result type, and cost. There is no filler or redundant information. It is front-loaded with the core purpose ('Ask Claude LLM any question') and efficiently communicates the key facts.

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 a single string parameter and an output schema, the description is quite complete. It covers the tool's purpose, the nature of the response (concise), and a cost indicator. It does not explain return structure, but the output schema covers that. The only notable gap is the lack of context about when to use this over ask_ai_pro, but overall it provides sufficient context for a simple AI-query 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 documents the only parameter 'q' with 'Your question', and the description adds no additional semantic detail beyond that. The phrase 'any question' simply reinforces the unrestricted nature of the input but does not introduce new constraints or format details, keeping this at baseline for high schema coverage.

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

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

The description clearly states the tool's function: 'Ask Claude LLM any question, concise answer.' This is a specific verb (ask) with a clear resource (Claude LLM) and outcome (concise answer), effectively distinguishing it from sibling tools like ai_image, ai_music, or ai_vision. The inclusion of cost (~$0.03) also provides practical context.

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 offers no explicit guidance on when to use this tool versus the sibling 'ask_ai_pro'. It says 'any question' but does not mention exclusions or alternatives, leaving the agent to guess whether ask_ai or ask_ai_pro is more appropriate for a given query. This lack of differentiation makes the usage guidance vague.

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

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

Annotations already convey non-destructive and open-world behavior. The description adds useful context: this is the strongest model and costs ~$0.05 per call, which helps an agent decide if it's worth the cost. It does not contradict annotations.

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?

One sentence with no fluff: it states the action, model tier, intended tasks, and cost. Every piece of information earns its place.

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 one-parameter query tool with an output schema and annotations, this description is complete: it tells the agent which model is used, what kinds of questions it handles, and the cost. No additional return-value details are needed.

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 'q' is fully documented in the schema as 'Hard question' (100% coverage). The description does not add parameter-level details, 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?

The description clearly identifies the tool as 'Ask the strongest Claude Opus model' and lists specific use cases ('complex analysis, code, reasoning'). This verb+resource phrasing distinguishes it from sibling tools like ask_ai or ai_vision.

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

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

The phrase 'complex analysis, code, reasoning' provides clear guidance on which tasks warrant this tool, and the cost (~$0.05) signals it's a premium option. However, it does not explicitly name alternatives or state 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?

Annotations declare openWorldHint=true and readOnlyHint=false, but the description adds cost (~$0.03) and answer conciseness, which are not captured in structured annotations. This provides useful operational 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 a single, purposeful fragment: 'Ask Google Gemini 3.1 Pro, concise answer. ~$0.03.' It conveys the model, output style, and cost in ten words, with zero 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 simple one-parameter tool with an output schema, the description is largely complete. It covers the core purpose and cost, though it omits any mention of response limits or rate constraints, which would be marginal for this 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% with q described as 'Your question'. The tool description does not add any additional semantic detail beyond what the schema already provides, so the baseline 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 identifies the action (ask), the target resource (Google Gemini 3.1 Pro), and the response style (concise answer), which distinguishes it from sibling ask_* tools like ask_gpt and ask_grok.

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?

There is no guidance on when to use this tool versus alternatives. It does not mention ask_gpt, ask_grok, or any selection criteria, leaving the agent without context for choosing this 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?

Annotations already set readOnlyHint=false and openWorldHint=true, so external/LLM behavior is known. The description adds the concrete cost (~$0.03) and the concise-answer trait, which are useful beyond the annotations and help set expectations.

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 entire description is one short sentence plus a cost qualifier, front-loading the core action and result. Every word adds value; 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?

Given the low complexity (one parameter, output schema present, annotations available), the description is adequately complete. It adds cost and output-style context, while return structure is presumably provided by the 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?

The schema fully covers the single parameter 'q' with description 'Your question', so the baseline applies. The description's 'any question' adds little beyond the schema, but no parameter meaning is missing.

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 names the action ('Ask OpenAI GPT-5.2'), the resource (the model), and the expected result ('concise answer'). Mentioning GPT-5.2 distinguishes it from sibling tools like ask_gemini and ask_grok.

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 it is for general questions where a concise answer from GPT-5.2 is desired, and the cost hint suggests lightweight use. However, it does not explicitly state when to prefer this over ask_ai, ask_ai_pro, or other 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?

Annotations already indicate readOnlyHint=false, openWorldHint=true, and destructiveHint=false, covering the safety profile. The description adds valuable behavioral context beyond annotations: the model version (Grok 4.6), tone ('witty'), speed ('fast'), and cost (~$0.03), which are not derivable from the structured fields.

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, compact sentence that delivers all key facts: the tool's purpose, the model version, the stylistic distinction, and the pricing. Every word earns its place, and it is front-loaded with the action verb 'Ask'.

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 one-parameter tool with an output schema and annotations, the description is sufficiently complete: it conveys what the tool does, its unique value proposition, and practical cost. It does not detail the return format, but the output schema presumably covers that, so no additional information is strictly required.

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

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

Schema description coverage is 100%: the only parameter 'q' is described as 'Your question'. The description does not add any extra meaning about the parameter, but since the schema fully documents it, a baseline of 3 is appropriate per the rubric.

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 function: 'Ask xAI Grok 4.6'. It uses a specific verb ('Ask') and resource ('xAI Grok 4.6'), and distinguishes it from sibling AI tools by emphasizing the 'witty alternative take' angle, making it clear this is a distinct AI model with a particular style.

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

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

The description implies usage context: choose this when you want a fast, witty response from Grok, and the cost hint (~$0.03) may influence decisions. However, it provides no explicit when-to-use or when-not-to-use guidance compared to sibling tools like ask_gpt or ask_gemini, leaving the selection criteria mostly implicit.

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

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

Annotations declare readOnlyHint=false and destructiveHint=false, so the description does not need to restate safety traits. It adds two valuable behavioral notes: 'paid per call' and 'ANY endpoint', which imply dynamic behavior and potential costs. No contradictions with annotations.

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 a clear prerequisite. Every word earns its place, and the structure is easy to scan.

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 openWorldHint, output schema, and sibling list, the description provides sufficient context: it mentions cost, prerequisite discovery, and the dynamic nature of the tool. It does not describe error cases or auth details, but those are not strongly needed with an output schema and generic endpoint semantics.

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 both parameters (path and query) with 100% coverage. The description adds little parameter-specific meaning beyond hinting at dynamic path discovery via list_endpoints, which is more about usage than parameter semantics. 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 uses a specific verb 'Call' with a clear resource 'ANY Reelfy endpoint by path with custom query parameters'. It distinguishes itself from siblings (e.g., 'list_endpoints', 'ai_image') by being a generic endpoint caller, and explicitly references a sibling tool as a prerequisite.

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 explicitly states 'Use list_endpoints first to discover paths and parameters', giving clear context for when this tool should be used relative to a sibling. However, it does not explicitly mention when not to use it (e.g., prefer a specialized tool when available).

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

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

Annotations are present (readOnlyHint=false, openWorldHint=true, destructiveHint=false), and the description adds cost ('~$0.005') and source (CoinGecko). However, it doesn't disclose data freshness intervals, rate limits, or the oddity that readOnlyHint=false for a read-only operation. The description is minimal but not contradictory.

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

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

One concise sentence that covers what, where, and cost. Highly efficient with no filler.

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?

The tool is simple with one optional parameter and an output schema exists, so the description doesn't need to explain return values. It mentions the key fields (USD, 24h change, market cap), source, and cost. Slightly incomplete due to the annotation mismatch, but overall sufficient for a simple price fetcher.

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% for the single 'ids' parameter, with its description already including format and default. The tool description adds no extra semantic meaning for the parameter, 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?

The description clearly specifies the tool returns live crypto prices with USD, 24h change, and market cap from CoinGecko. It distinguishes itself from generic web tools by focusing on crypto data, though it doesn't explicitly name sibling alternatives like market_snapshot.

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. It doesn't mention situations where this should be preferred (e.g., for CoinGecko data) or excluded (e.g., when broader market data is needed). The cost hint is useful but not a usage 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?

Annotations include readOnlyHint: false, destructiveHint: false, and openWorldHint: true. The description adds cost (~$0.005) and the protocol (WHOIS/RDAP), which goes beyond the annotations. It does not contradict the annotations; readOnlyHint false isn't contradicted because the description never claims to be read-only. The cost disclosure is useful behavioral information.

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 entire description is a single sentence that front-loads the core purpose ('WHOIS/RDAP dossier') and lists key data points concisely. Cost information is included at the end. There is no wasted words 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?

For a single-parameter lookup tool with an output schema and annotations, the description covers the essential purpose, outputs (registrar, dates, status, nameservers), and cost. It is sufficiently complete for an AI agent to decide whether to invoke it and what to expect. The simplicity of the tool doesn't require additional context.

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% and the only parameter 'domain' has a clear description in the schema ('Domain name, e.g. example.com'). The tool description doesn't add additional parameter details, so it meets the baseline but doesn't exceed it.

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 a WHOIS/RDAP dossier for a domain, listing specific data points (registrar, creation/expiry, status, nameservers). This distinguishes it from sibling tools like web_search or scrape_page, which handle different kinds of lookups.

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

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

The description implies when to use the tool: when you need domain registration details. It does not mention alternatives or exclusions, but the specific scope (WHOIS/RDAP) makes the usage context clear. Since it's a single-purpose tool among less similar siblings, this is adequate.

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

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

Annotations are present (readOnlyHint: false, openWorldHint: true, destructiveHint: false), but the description adds useful context like 'free, no payment' and 'live prices', implying a network read operation. However, it does not explicitly state what side effects (if any) exist, though listing is inherently non-destructive.

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 core action ('List ALL') and includes necessary details without fluff. Every word earns its place.

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 (0 params, output schema present), the description provides sufficient context: what is listed, scope, price info, example URLs, and cost. The output schema covers return structure, so the description is complete.

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

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

The tool has zero parameters, so the description need not explain parameter meaning. It does add value by describing the output content (live prices, example URLs), which is helpful despite no params.

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 'List ALL Reelfy paid endpoints' with a specific verb and resource, and adds that it provides 'live prices and example URLs'. It is easily distinguished from sibling tools like call_endpoint or web_search.

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 (you can see all paid endpoints and prices) but does not explicitly state when to use this over alternatives such as call_endpoint. No direct 'use this when...' or 'instead of...' guidance is provided.

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?

Annotation Contradiction: The annotation declares readOnlyHint=false, yet the description characterizes the tool as a 'snapshot' which implies read-only, non-mutating behavior. This is a direct contradiction. The cost disclosure (~$0.02) is useful but does not resolve the inconsistency.

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

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

The description is extremely concise and well-structured: the first sentence conveys the complete functionality, the second adds pricing. Every word earns its place with no fluff.

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, one-optional-parameter tool with an output schema, the description covers the key features and pricing. However, the contradiction with the readOnlyHint annotation leaves a gap about side effects, slightly reducing completeness.

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

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

Schema coverage for the single optional 'ids' parameter is 100%, with the schema already providing 'Coin ids to include'. The description adds no additional parameter semantics, but the high schema coverage justifies a 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's purpose: a single-call crypto market snapshot combining prices, fear/greed index, trending, and BTC fees. It uses a specific verb ('snapshot') and enumerates the resources, effectively distinguishing it from the sibling crypto_prices tool which likely only provides price 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 phrase 'in one call' implies usage for consolidated market data retrieval, making it clear when to prefer this over separate price queries. While it doesn't explicitly name alternatives or exclusions, the sibling context and the description provide sufficient usage context.

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 annotations (readOnlyHint=false, openWorldHint=true, destructiveHint=false) already outline the overall safety profile. The description adds valuable context beyond these: it reveals the output format ('transparent result') and the financial cost ('~$0.10'), which are useful behavioral details. It does not cover rate limits or error handling, but that's acceptable for such a simple 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 one efficient sentence that front-loads the core action ('Remove the background'), immediately states the outcome ('transparent result'), and appends the cost. Every word earns its place; there is no superfluous text.

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 a single parameter and an existing output schema, the description covers the essential context: purpose, result type, and pricing. It omits edge cases like file format constraints or size limits, but those are not critical for a basic invocation and would likely be covered by error messages or additional documentation.

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 fully documents the single required parameter 'image' with the description 'Public URL of the image' at 100% coverage. The tool description does not add further parameter-specific semantics, but the schema already provides sufficient meaning, so the baseline 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 action: 'Remove the background from an image.' It specifies the outcome ('transparent result') and even notes the cost ('~$0.10'), giving a precise, self-contained purpose. No sibling tool overlaps with this functionality, so it stands alone.

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 clearly implies the use case: when you need to remove an image background. It does not explicitly name alternatives or exclusion criteria, but none of the sibling tools offer similar functionality, making this guidance adequate.

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

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

Annotations already indicate openWorldHint=true and destructiveHint=false. The description adds valuable behavioral context: it performs 3 live web searches, generates a brief via Claude, includes citations and source links, and costs approximately $0.10. No contradiction with annotations.

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 short, front-loaded phrases that convey the core behavior, output characteristics, and cost without redundancy. Every word earns its place.

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 multi-step research tool, the description covers the essential behavior (3 searches, AI-written brief, citations, cost). An output schema exists to define the return format, so the description doesn't need to. It lacks only explicit guidance on usage scenarios, but is otherwise complete for its complexity.

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

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

The schema fully covers the single parameter 'q' with description 'Research topic', providing 100% coverage. The tool description does not add additional meaning, examples, or format details beyond the schema, 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?

The description clearly identifies this as an automated research tool: it performs 3 live web searches and produces a Claude-written brief with citations and source links. This distinguishes it from siblings like web_search (single search), scrape_page (scraping), and ask_ai (general Q&A).

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 context is implied: it is for research requiring multiple web searches and a synthesized brief. However, the description provides no explicit when-to-use vs alternatives or exclusions, such as when a single web search or ask_ai would be more appropriate.

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

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

Annotations already declare non-read-only and non-destructive behavior. The description adds value by disclosing cost (~$0.005) and the promise of 'clean content' (preprocessing). It does not contradict annotations and provides useful operational 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, front-loaded with the action and resource, and ends with the cost. Every word earns its place; no repetition of schema details or unnecessary elaboration.

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

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

Given the tool's simplicity (one parameter) and the presence of an output schema, the description sufficiently conveys the main behavior and cost. It omits error handling or edge cases, but these are not critical for a straightforward fetch operation, and the schema covers return 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?

The schema covers the single parameter 'url' with a description ('Full page URL'), achieving 100% coverage. The description simply restates 'web page' without adding constraints or format details, so the schema alone is sufficient and the description adds no extra semantics.

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 fetches a web page and returns clean content (title, headings, text, links). The verb 'Fetch' and resource 'web page' are specific, and the output list distinguishes it from sibling tools like web_search or domain_info.

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 context is implied rather than explicit: it's for retrieving content from a specific URL. However, there is no mention of when to use this over alternatives, no exclusions, and no comparison to web_search or research_report, which limits 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?

Annotations already indicate open world and non-destructive behavior, but the description adds cost (~$0.005) and output format ('short AI answer'), which are useful behavioral details. No contradictions with annotations.

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, information-dense sentence that front-loads the core function. No filler or redundant content.

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 one-parameter tool with an output schema and annotations, the description captures the essential behavior (fresh results, AI answer, cost). It is sufficiently complete given the tool's simplicity.

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 has 100% coverage with a description for q ('Search query'). The description does not add further parameter details, so it meets the baseline for high schema coverage.

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

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

The description clearly states a specific action ('web search') and resource ('web'), and notes it returns live results plus an AI answer. This distinguishes it from other sibling tools like ask_ai or research_report.

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 'Live web search' implies it is for up-to-date information from the web, providing context for when to use it. It does not explicitly exclude alternatives or mention when not to use it, so it falls 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.