Studio MCP Hub Site

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, covering the safety profile. The description adds cost (($5.00 / 50 GCX)) and a minimum quantity constraint, which are useful behavioral details beyond what annotations provide. No 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?

Description is a single concise sentence that efficiently conveys the core action, dataset, and key constraint. The cost note is included without unnecessary 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?

With good annotations and 100% schema param coverage, the description sufficiently covers purpose, resource, min quantity, and cost. It does not describe the return format (e.g., zip file, URLs), which is a minor gap given no output schema, but overall it is complete for a bulk download tool.

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

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

Schema description coverage is 100% for all 3 parameters (offset, quantity, dataset_id), each with clear descriptions. The description adds no extra parameter semantics beyond restating the min 100, so baseline 3 applies.

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 performs a bulk download of metadata + images from Alexandria Aeternum, with a minimum quantity of 100 artworks. It uses a specific verb ('download') and resource, distinguishing it from siblings like get_artwork or search_artworks.

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 bulk operations via the word 'Bulk' and the min 100 constraint, but it does not explicitly state when to use this tool over alternatives or provide exclusions. It would benefit from saying 'use for large downloads; for single artwork use get_artwork'.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the agent knows this is a safe, non-mutating operation. The description adds a list of what is checked (credit balance, rewards, tier) but does not disclose any additional behavioral traits such as return format, network requirements, or limitations. It does not contradict 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?

The description is concise and front-loaded with the key purpose. However, the phrase 'FREE. (FREE)' is redundant and adds no value, making it slightly less polished than a perfectly concise description.

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 read-only tool with one parameter and no output schema, the description is sufficiently complete. It tells the user what information can be retrieved. It does not describe return values, but that is not required given the simplicity and lack of output schema. A small gap is the absence of any note about the response format or whether the wallet must be registered.

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 provides 100% coverage for the only parameter 'wallet' with a description ('Your EVM wallet address (0x...)'). The tool description does not add any further meaning beyond the schema, so the baseline score of 3 applies.

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: 'Check your GCX credit balance, loyalty rewards, and volume tier.' It uses a specific verb ('check') and resource (balance/rewards/tier), and this is the only balance-checking tool among siblings, so it is well-distinguished.

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 the tool should be used when a user wants to see their GCX credit balance, loyalty rewards, or volume tier, but it provides no explicit guidance on when to use it versus alternatives or any prerequisites. There are no competing tools for this purpose, but the usage context is only 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?

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so safety is covered. The description adds regulatory scope (AB 2013, EU AI Act) but does not disclose additional behavioral traits such as response format, pagination, or authentication requirements. It does not contradict 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?

The description is short but contains redundant 'FREE. (FREE)' text that adds no value and appears as filler. The core sentence is concise, but the repetition is unprofessional and wastes space.

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 simple read-only nature, annotations cover safety, and schema fully documents parameters, the description sufficiently conveys what the tool does. It does not describe return format, but for a straightforward manifest-fetching tool with no output schema, the core purpose is clear enough. The 'FREE' noise slightly detracts from 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 description coverage is 100%, so parameter meanings are fully documented in the schema. The description does not add syntax, formatting, or extra context beyond what the schema provides. 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 retrieves compliance manifests for AB 2013 and EU AI Act Article 53, with a specific verb ('Get') and resource ('compliance manifests for dataset usage'). This is distinct from sibling tools like verify_provenance or get_asset, making the purpose unambiguous.

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

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

The description provides no guidance on when to use this tool versus alternatives. It does not mention exclusions or scenarios where another tool (e.g., verify_provenance) would be more appropriate, nor does it state prerequisites or context for requesting compliance manifests.

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 the tool as read-only, idempotent, and non-destructive. The description adds a useful behavioral detail: 'CMYK output as TIFF with embedded DPI,' which explains the output format. However, it does not fully disclose the behavior for sRGB output or other edge cases, and the 'FREE' text is irrelevant.

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 generally concise and well-structured, with a clear purpose, context, and output detail. However, the repeated 'FREE. (FREE)' is redundant and detracts from conciseness, preventing a perfect score.

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 description explains the core functionality and the CMYK output format, but it lacks important details such as the return format (e.g., base64 string, file URL) and what happens when converting to sRGB. Since there is no output schema, the description should cover these aspects more thoroughly.

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 parameters are already well-documented. The description adds marginal value by mentioning 'embedded DPI,' which reinforces the dpi parameter's role, but it does not provide substantial additional meaning beyond what the schema already says.

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: 'Convert between sRGB and CMYK color profiles.' This is a specific verb + resource that distinguishes it from sibling tools like extract_palette or remove_background. The additional context about print production and TIFF output further clarifies its role.

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 by stating 'Essential for print production,' which tells the user when to use this tool. However, it does not explicitly mention when not to use it or name alternatives, such as print_ready, so it does not fully meet the top criterion.

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

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

The annotations already declare destructiveHint=true, readOnlyHint=false, and idempotentHint=true. The description merely repeats the concept of deletion ('Delete an asset') without adding any extra behavioral context such as permanence, irreversibility, or storage implications. The 'FREE' text adds noise, not transparency.

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 short but contains redundant filler: 'FREE. (FREE)' is completely irrelevant to the tool's function and should be removed. A concise description should make every word count; these extra sentences fail to earn their 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 two-parameter delete operation, the description is minimally viable. It states the action and target storage location, and the schema covers parameter details. However, it lacks an explicit statement about permanence or potential side effects, though the destructive annotation partially compensates. No output schema means the description could also mention that no return value is expected.

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 'key' and 'wallet' parameters with clear descriptions. The tool description does not add any additional parameter semantics, but the baseline of 3 is appropriate because the schema already supplies the necessary meaning.

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

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

The description clearly states the primary action ('Delete an asset') and the resource affected ('from your wallet storage'). This distinguishes it from sibling tools like get_asset, save_asset, and list_assets, which involve different operations.

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 alternatives, nor any mention of prerequisites or consequences. The tool name and schema imply deletion, but there is no explicit 'use this when you want to permanently remove an asset' or 'this deletes by key and wallet' 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 description adds useful context beyond annotations: pricing ($0.20 / 2 GCX), the underlying AI models (Nova-Lite vs. Nova/Gemini), and default premium tier. However, it does not disclose the actual side effects of the operation—whether it modifies the asset's metadata, returns the generated metadata, or requires ownership. Given that readOnlyHint=false, the description should clarify what non-read-only action occurs, which it does not.

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 dense sentence that packs in tiers, costs, models, customization, and pricing. It is reasonably concise but structurally cluttered—the pricing notation '($0.20 / 2 GCX)' is confusingly appended at the end. The information is front-loaded with 'AI-powered artwork analysis' but the run-on style reduces clarity.

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 parameters, nested objects, two tiers, no output schema), the description covers the main purpose and tier selection well but omits key operational details: what the tool returns (metadata fields? updated asset?) and whether it writes to the asset. It also doesn't mention authentication requirements or prerequisites beyond the image. The missing output behavior is a notable gap.

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, so the schema already explains all 9 parameters. The description adds value by naming the tiers and their cost, and by mentioning customization of metadata fields, but it does not provide additional details about parameter syntax or format beyond what the schema already contains. This aligns with the baseline score of 3 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 it performs AI-powered artwork analysis to generate metadata, with specific outputs (SEO-optimized title, description, keywords, alt_text) and a premium tier producing 'Golden Codex' analysis. The verb 'analysis' is less direct than 'enrich' but is specific enough to convey the resource (artwork) and action. It does not explicitly differentiate from sibling tools like infuse_metadata, so it loses a point for missing sibling distinction.

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 usage context by explaining the two tiers (standard vs. premium) and their respective outputs, helping agents choose based on cost and depth. It also mentions optional customization and Soul Whisper, which guides when to use these features. However, it does not explicitly state when to use this tool over alternatives such as infuse_metadata, so it falls short of a perfect score.

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

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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior. The description adds valuable behavioral details beyond that by specifying the output: 'hex/RGB/HSL colors with percentages, CSS names, and complementary colors.' It also mentions 'FREE' as a pricing/safety signal. 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 compact overall, but 'FREE. (FREE)' is redundant and wastes space, violating the principle that every sentence should earn its place. The rest is front-loaded with the core purpose and output details, but the repetition lowers the score.

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 no output schema, the description appropriately explains the return values ('hex/RGB/HSL colors with percentages, CSS names, and complementary colors'). It covers the core functionality and use cases. Though it doesn't specify the exact JSON structure, the level of detail is sufficient for a moderately complex tool with good annotations.

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

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

Schema description coverage is 100%, so the schema fully documents all three parameters (image, format, num_colors). The description mentions hex/RGB/HSL which aligns with the format enum, but adds no new meaning beyond the schema. Baseline of 3 is appropriate since the schema does the heavy lifting.

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

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

The description clearly states the tool's function with a specific verb and resource: 'Extract dominant color palette from an image.' This distinguishes it from sibling tools like convert_color_profile or resize_image, making the purpose unmistakable.

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

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

The description gives clear application contexts: 'Great for design systems, mood boards, and color matching.' It implies when to use the tool, though it does not explicitly state when not to use it or mention alternatives. This is solid guidance but lacks explicit 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?

The annotations already declare readOnly, non-destructive, and idempotent behavior. The description adds valuable behavioral context—output size (500-1200 tokens), the signed image URL aspect, and the cost ($0.10 / 1 GCX)—which goes beyond what annotations provide. It does not detail URL expiry or auth, but given strong annotations, this is acceptable.

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, well-structured sentence that packs in the resource, outputs, token count, and cost without redundancy. Every phrase 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 read-only tool with one parameter and existing annotations, the description and schema are sufficient to invoke the tool correctly. It names the return values at a high level and notes pricing. It could have explained Human_Standard or URL expiry, but these are not essential for using the 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% with a clear description and example ('Artifact ID from search results (e.g. 'met_437419')'). The tool description adds no additional parameter meaning beyond the schema, but the baseline of 3 applies since the schema already does the heavy lifting.

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

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

The description uses a specific verb ('Get'), names the resource ('museum artwork'), and states the exact outputs ('Human_Standard metadata (500-1200 tokens) + signed image URL'). This clearly distinguishes it from sibling tools by anchoring to museum artwork and the Human_Standard format.

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

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

No explicit when-to-use or when-not-to-use guidance is provided. The description only states what the tool does, without mentioning alternatives like get_artwork_oracle or get_asset, or any prerequisites/conditions for use.

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 read-only, idempotent, non-destructive behavior. The description adds cost ($0.20/2 GCX), output size (2K-6K tokens), and the inclusion of an image, which are not in annotations. No 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 two sentences, front-loading the main deliverable and then detailing features and cost. 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?

Given the tool's complexity and absence of an output schema, the description specifies the analysis fields, token range, and image inclusion. It does not detail the output format, but provides sufficient context for an agent to anticipate results.

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 is fully described in the schema with an example. The description adds no parameter-specific information, so baseline 3 applies.

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 this tool retrieves a structured analysis ('111-field NEST analysis') plus an image. The specific components (color palette, composition, symbolism, emotional mapping) distinguish it from siblings like extract_palette or get_artwork.

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 deep AI visual analysis of artwork, with cost and token range providing context. It does not explicitly name alternatives or exclusions, but the 'Deep AI' phrasing signals it is for comprehensive analysis beyond basic retrieval.

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 cover read-only, idempotent, and non-destructive behavior. The description adds minor context by indicating the asset is from 'your wallet storage' (ownership scope) and repeats 'FREE', which may refer to cost. However, it does not disclose return format, prerequisites like wallet registration, or failure behavior.

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

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

The description is a single, short sentence that gets to the point quickly. The only minor issue is the redundant 'FREE. (FREE)' repetition, which adds noise but does not significantly impact clarity.

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 getter with only two parameters and a read-only annotation, the description is adequate but lacks mention of return format or error behavior. Since there is no output schema and no explicit description of what the caller receives, this is a clear gap.

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 fully (100% coverage). The description only confirms that lookup is 'by key' and storage is in 'wallet storage', adding little beyond the schema's own 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 uses a specific verb ('Retrieve'), identifies the resource ('stored asset from your wallet storage'), and specifies the lookup mechanism ('by key'). This clearly distinguishes it from siblings like save_asset, delete_asset, and get_artwork.

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 the tool should be used when you have a wallet address and an asset key to fetch a stored asset, but it does not explicitly state when to prefer this over alternatives like list_assets or get_artwork. No when-not or alternative 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?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the agent knows this is a safe read operation. The description adds minimal behavioral context (e.g., 'FREE' and 'load only what you need') but does not contradict annotations. With annotations covering the safety profile, a score of 3 is appropriate.

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 and includes a practical usage hint. Every word earns its place; there is 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?

For a simple read-only tool with one parameter, strong annotations, and no output schema, the description is complete. It clearly states what the tool returns (schema + usage examples) and when to use it, covering the essentials.

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% for the single parameter tool_name, so the schema already fully documents it. The description adds no additional parameter semantics beyond what's in the schema, so the 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 the specific verb 'Get' and names the resource 'full JSON Schema and usage examples for a specific tool', making its purpose immediately clear. It also distinguishes itself from the sibling tool search_tools by explicitly positioning itself as the follow-up step after searching.

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 states when to use the tool: 'Use after search_tools to load only what you need.' This provides a clear workflow and differentiates it from the search tool, giving the agent actionable 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?

Annotations already indicate a non-read-only, non-destructive, idempotent operation. The description adds cost ($0.10 / 1 GCX), mode details (XMP/IPTC, C2PA, soulmark, hash registration), and the ExifTool implementation, which are useful beyond the annotations. It does not disclose output/return behavior, but the annotations cover the core safety profile.

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

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

The description is compact, front-loaded with the main action, and every sentence adds value. Mode explanations and cost are provided without unnecessary elaboration.

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

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

With 3 parameters, a nested metadata object, and no output schema, the description covers modes but omits return behavior and prerequisites. It references enrich_metadata in the schema, aiding workflow context, but gaps remain regarding what the tool outputs or how the image is modified.

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

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

Schema description coverage is 100%, so the schema already explains all parameters. The tool description adds marginal detail about the full_gcx mode (e.g., XMP-gc namespace, C2PA, soulmark), but does not significantly change parameter understanding. 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 tool's purpose with a specific verb ('Embed metadata into image') and mechanism ('via ExifTool'). It distinguishes this tool from siblings like enrich_metadata and watermark_embed by focusing on the infusion step and naming two distinct modes.

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

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

The description implies use when metadata needs to be embedded, but it does not explicitly contrast with sibling tools or state when not to use it. The two modes provide internal guidance for standard vs full_gcx, but no alternative tool selection criteria are mentioned.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the description is not required to restate safety. It adds useful output detail ('sizes and metadata') and scoping ('wallet storage'), but lacks information about pagination, rate limits, or authentication requirements beyond the required wallet parameter.

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 and front-loaded with the main action, but it contains redundancy with 'FREE. (FREE)' which adds no informational value and appears twice. This repetition is a minor structural flaw that prevents a higher score.

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 low-complexity tool with a single parameter and good annotations, the description provides sufficient context: it explains what is listed (all assets) and what output to expect (sizes and metadata). No output schema exists, but the description compensates. It does not mention pagination, but the tool's simplicity makes this omission acceptable.

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% for the single 'wallet' parameter, so the schema fully documents it. The description does not add further semantic detail about the parameter beyond what the schema already provides, leading to 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 verb 'List' and the resource 'assets in your wallet storage' with additional detail 'sizes and metadata'. This distinguishes it from sibling tools like get_asset (single asset) and search_artworks (search), making the purpose unambiguous.

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

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

The description implies when to use the tool (to list all assets in wallet storage) but does not explicitly mention when to avoid it or provide alternatives. No direct comparison with get_asset or other listing/search tools is given, so usage guidance is only 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?

The annotations already declare the tool as read-only, idempotent, and non-destructive. The description adds context about cost (FREE with a GCX fee) and instant speed, but does not disclose details about output format or file handling, which is a minor gap given no output schema.

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

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

The description is compact, front-loads the primary purpose, and organizes additional context (use case, pricing) in short sentences. The pricing note 'FREE' is extra but not detrimental.

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 three parameters, full schema coverage, and helpful annotations, the description adequately explains the core function and use case. However, it omits details about the output format or any image requirements, which would be useful given the absence of an 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 input schema fully documents all three parameters, including descriptions, types, enums, and defaults. The description repeats the product list but adds no new semantic information about how to use the parameters, so it meets the baseline for schema coverage.

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

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

The description clearly states the tool's purpose with a specific verb ('Place') and a defined resource ('your design onto product mockups'), and enumerates the supported product types. This makes it distinct from sibling tools, none of which offer mockup 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?

It provides a clear use case for e-commerce and print-on-demand, which signals when to employ this tool. However, it does not explicitly name alternatives or exclusions, though no sibling tool offers mockup functionality.

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 provide readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds no further behavioral details (e.g., side effects, limitations, file size caps) beyond the transformation options. The repeated 'FREE' is irrelevant and doesn't contribute behavioral transparency. With good annotation coverage, the added value is limited.

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 core description is a compact two sentences that effectively cover the tool's capabilities. However, the 'FREE. (FREE)' is duplicative noise that doesn't add value, detracting from the overall conciseness. It earns a 3 rather than a 4.

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 8 parameters and no output schema, the description covers the primary capabilities and supported options. It mentions output formats (TIFF/PDF) and paper sizes, which aligns with schema enums. It stops short of explaining the response structure (e.g., a download link or binary), but given the rich schema and annotations, the description is reasonably complete for an initial understanding.

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 each parameter has a description. The description mentions DPI, bleed, crop marks, sizes, and output formats, but these are also in the schema. It doesn't add meaning beyond the schema, such as explaining the custom size dependency or the base64 encoding requirement. 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 ('Prepare') and resource ('images for professional printing') and lists concrete processing details (DPI, bleed margins, crop marks). This clearly distinguishes it from sibling tools like resize_image or convert_color_profile. It also mentions output formats and supported paper sizes, making the tool's scope unmistakable.

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 'for professional printing' clearly frames when this tool should be used. It doesn't explicitly name alternatives or when-not-to-use, but the print-specific context is enough to infer it's the right choice for print-ready output. Could be improved by explicitly contrasting with resize_image/convert_color_profile, but that's not required for a clear 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?

Annotations already establish the read/write safety profile (readOnly=false, destructive=false, idempotent=true). The description adds valuable behavioral context: the $0.10 cost, the specific LSH band indexing technique, and the 'strip-proof provenance' purpose, which go beyond what annotations convey.

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 that are front-loaded with the action and purpose. The cost note is included without redundancy. Every word contributes meaning, making it efficiently structured.

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

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

Given the simple single-parameter schema and annotations that cover safety and side-effect hints, the description adequately explains the core function and cost. However, it does not mention expected return values or next steps, which would improve completeness given there is no 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 covers 100% of the single parameter 'image' with a clear description ('Base64-encoded PNG/JPEG image'). The tool description adds no further parameter-level details, so the baseline score of 3 applies.

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

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

The description clearly states the verb 'Register' and the specific resource '256-bit perceptual hash with LSH band indexing', making the tool's function unambiguous. It also distinguishes this tool from siblings like verify_provenance by focusing on the registration step.

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 strip-proof provenance registration but does not explicitly state when to use this tool over alternatives or mention exclusions. It provides context but lacks direct comparative 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?

Discloses the reward (10 GCX credits), the restriction (new wallets only), and promotional context beyond annotations. Annotations don't cover these specifics, so the description adds meaningful behavioral context.

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

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

The description is front-loaded but contains redundant promotional text at the end ('FREE. (FREE)'), which doesn't add value. Could be trimmed to a more concise statement.

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 registration tool with no output schema, the description covers purpose, eligibility, and benefit adequately. It doesn't explain success/failure responses, but that's a minor gap given the 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 already covers the single parameter 'wallet' at 100% with description. The tool description does not add additional parameter semantics, so baseline 3 applies.

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?

Clearly states 'Register your wallet' with a specific verb and resource, and adds the purpose (get 10 FREE GCX credits). Distinguishes from siblings by being the only wallet registration tool.

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?

Specifies 'New wallets only' and suggests use for trying upscale and enrich, with alternative to purchase more via GCX packs. Could be more explicit about when not to use (e.g., existing wallets), but the constraint is clear.

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

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the description adds value by disclosed the return format (RGBA PNG/WebP). No contradictions; the redundant 'FREE' text doesn't affect behavioral transparency.

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 mostly succinct but includes redundant 'FREE' and '(FREE)' text that wastes space and doesn't aid an AI agent. The structure is a bit fragmented, so it doesn't earn a 4.

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 tool with two params and strong annotations, the description adequately covers the operation, return format, and use cases. It lacks mention of size limits or edge cases, but that's not critical for a straightforward image processing 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 covers 100% of parameters with descriptions for both image and output_format. The description only reiterates the output formats already enumerated in the schema, so it adds no meaningful beyond 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?

Description uses a specific verb ('Remove') and resource ('image background'), names the AI method (U2-Net), and specifies output format (RGBA PNG/WebP). This clearly distinguishes it from sibling tools like resize_image or convert_color_profile.

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?

Provides clear use cases ('Perfect for product photos, portraits, and design assets') but does not explicitly state when not to use or name alternatives. Context is sufficient for basic selection.

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

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

The description explains the behavioral differences between fit modes (crop, letterbox, stretch), which adds value beyond the readOnly/idempotent annotations. It does not contradict 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?

The description is mostly concise but ends with 'FREE. (FREE)', which is redundant and wastes space. This prevents a higher score.

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 rich schema and annotations, the description adequately covers when and how to use the tool. It doesn't mention output details, but no output schema exists and the schema covers input constraints.

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 restates the mode semantics but does not add new parameter-level detail 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?

The description clearly states the tool resizes an image to target dimensions and lists the supported fit modes. However, it does not explicitly differentiate itself from sibling tools like upscale_image, which also modifies image dimensions.

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 use-case context ('preparing images for specific platforms, thumbnails, or social media') but does not exclude alternative use cases or mention when to prefer a sibling tool.

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

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

Annotations already indicate this is a write (readOnlyHint=false), idempotent, and non-destructive. The description supplements with important behavioral constraints: storage quotas (100MB free, 500 asset max) and cost ($0.10/1 GCX). These go beyond annotations and help the agent understand limits and pricing.

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?

Three short sentences, all informative. The purpose is front-loaded, and the additional sentences provide concrete limits and cost without fluff. Every sentence 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?

The description covers purpose, storage limits, and cost, which are key context for a save operation. With annotations present and schema covering parameters, it is adequate. It does not explain return values or overwrite behavior, but those are either inferable from idempotentHint or non-critical for a simple save tool.

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

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

Schema description coverage is 100%, so the schema already documents all parameters. The description does not add parameter-specific detail beyond mentioning 'image or data' which maps loosely to the data parameter. 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 verb ('Save') and resource ('personal wallet storage'), and identifies the payload ('image or data'). It distinguishes from sibling tools like get_asset, delete_asset, and list_assets by explicitly conveying a write/storage action.

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 (use this to store assets) but does not explicitly contrast with alternatives or state when not to use it. No mention of sibling tools or conditions like 'for retrieval use get_asset'. Guidance is only implicit in the purpose statement.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds the specific data sources (MET, Chicago, NGA, etc.) and the volume (53K+), but does not disclose behavioral traits like rate limits, pagination, or return format. 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?

The first sentence is efficient and front-loaded with purpose. The second sentence 'FREE. (FREE)' is redundant and adds no value, a minor flaw. Overall, the description is short and mostly concise, with one piece of waste.

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 3 well-documented parameters and full annotation coverage. The description adds the museum sources and scale, which is useful context. Without an output schema, the description doesn't need to explain return values. A small gap is that the return format is not mentioned, but schema and simplicity make this acceptable.

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

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

Schema description coverage is 100%, so all three parameters (query, limit, museum) have descriptions in the schema. The tool description adds no extra parameter-level semantic detail beyond the schema. Baseline is 3 given 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: 'Search 53K+ museum artworks' with a specific resource (museum artworks) and scope (the listed museums). This distinguishes it from sibling tools like get_artwork (which likely fetches a specific artwork) and search_tools (which searches for tools). The verb 'search' and the resource are explicit and unambiguous.

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

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

The description implies usage is for searching museum artworks but does not explicitly state when to use this tool versus alternatives. No exclusions or comparisons to siblings are provided. The context is clear from the name and description, but the guidance is not 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 declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so safety is covered. The description adds useful context beyond annotations: it is '(FREE)' and it avoids loading all schemas, which signals low cost and lightweight behavior. 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, concise sentence with a parenthetical note. It is front-loaded with the core purpose and includes only high-value information (token savings, free). 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 (three optional params, no output schema), the description adequately covers its role as a discovery tool. It explains why to use it (saves tokens) and what it does (finds tools by category/price). It doesn't describe return format, but for a meta-tool used to browse the catalog, 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%, with each parameter (query, category, max_price_usd) already documented. The description adds minimal extra meaning by referencing 'by category or price', which maps to category and max_price_usd, but this is redundant with the schema. 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 tool's function: 'Discover available tools by category or price'. This uses a specific verb ('Discover') and resource ('available tools'), and distinguishes it from siblings like search_artworks (which searches artworks) and get_tool_schema (which loads a specific schema).

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

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

The description gives a clear usage directive: 'Start here to save tokens', implying this should be the first tool used before loading individual schemas. It also contrasts with loading all schemas, indicating when it is useful, though it doesn't 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 declare readOnlyHint=false, idempotentHint=true, and destructiveHint=false. The description adds valuable context: it runs on an NVIDIA L4 GPU, costs $0.20 per 2 GCX, and offers model variety. This goes beyond the annotations, though it doesn't disclose output format or potential side effects beyond cost.

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, dense sentence that conveys the core functionality, hardware, model options, default behavior, and pricing. No filler words; every piece of information is useful.

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 a fully documented schema and annotations, the description provides pricing, default behavior, and model selection context. The main gap is the absence of output format or how the upscaled image is returned, but the description is otherwise complete for an agent to 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 description coverage is 100% and each parameter (image, model, scale) is thoroughly described with defaults and enum options. The description merely restates the default (2x general upscale) and model count, adding no new meaning 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 explicitly states 'Super-resolution using Real-ESRGAN' with the resource (image), mentions 5 models for different content types, and the default 2x scale. This clearly differentiates it from sibling tools like resize_image or vectorize_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?

Usage is implied through 'Super-resolution' and model selection, but there is no explicit guidance on when to use this tool versus alternatives (e.g., resize_image for simple dimension changes) or any exclusion criteria. The description does not name sibling tools or provide when-not-to-use conditions.

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 read-only, idempotent, non-destructive. The description adds that it returns raw SVG XML and supports color/binary modes, providing useful behavioral context beyond 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 concise with two sentences that get to the point, though the repeated 'FREE' inline is redundant and unpolished.

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, the description covers the return format and main capability. No output schema exists, so explaining the raw SVG string return is important. The annotations cover safety aspects.

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 descriptions for all 4 parameters. The description mentions modes and precision controls but adds no specific 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?

The description uses the specific verb 'Convert' and resource 'raster images to SVG vector format', clearly defining the tool's function and distinguishing it from sibling image tools like resize_image or remove_background.

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 that this tool is for vectorization but does not explicitly state when to use it over alternatives or mention any exclusions, so it lacks explicit usage 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 declare readOnlyHint, idempotentHint, and openWorldHint, so the safety profile is covered. The description adds that it uses an Aegis hash index and is free, but does not disclose what happens when verification fails or whether it contacts an external service. No contradiction with annotations is present.

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

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

The description is short but contains redundancy: 'FREE - no payment required' is repeated in '(FREE)' at the end. This duplication wastes words and detracts from the clarity of the core purpose. Otherwise, it is front-loaded with the primary action.

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?

There is no output schema, so the description must explain what the tool returns, but it does not specify whether the result is a boolean, a hash match, or other data. It also fails to mention any caveats around the verification process, making it incomplete for an agent to know what to expect from the call.

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 a 100% description coverage for the single 'image' parameter, so the schema already explains that it expects Base64-encoded PNG/JPEG. The description adds nothing about parameters, which is acceptable given the schema coverage, but it could have clarified the image format or constraints for the hash index verification.

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 performs provenance verification using an Aegis hash index, which is a specific action on a specific resource. It distinguishes from sibling tools like register_hash by focusing on verification rather than registration, though the term 'strip-proof' is jargon and could be clearer.

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

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

The description provides no guidance on when to use this tool versus alternatives. It does not mention any exclusions, prerequisites, or comparisons with sibling tools like register_hash or watermark_detect. The only extra information is a redundant statement about being free, which is not usage 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 read-only, idempotent, and non-destructive behavior. The description adds useful context by specifying the watermark type (invisible DCT) and the return payload, which are not captured in the annotations. It does not contradict the annotations, and the 'FREE' repetition is noise but not misleading.

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 core description is succinct and front-loaded with the key purpose. However, the repeated 'FREE. (FREE)' is redundant and does not earn its place, reducing the overall conciseness score.

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 simple one-parameter read-only tool with strong annotations, the description covers purpose, method, and return value. It could mention failure behavior when no watermark is found, but the current wording is sufficient for basic invocation. The absence of an output schema is mitigated by the explicit return description.

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

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

Schema coverage is 100% (single 'image' parameter with a clear description). The tool description does not add parameter-specific details beyond the schema, so it meets the baseline without adding extra semantic value.

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: detect and extract an invisible DCT watermark from an image, with a specific output (embedded text payload). It distinguishes itself from sibling watermark_embed by focusing on detection rather than embedding.

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 extracting a watermark but does not explicitly state when to prefer this tool over alternatives (e.g., watermark_embed). No exclusions or alternative tool mentions are provided, making the guidance implicit 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 declare readOnlyHint=true, but the description indicates a write operation ('Embed invisible... watermark into an image'). This is a direct contradiction; the tool modifies the image and is not read-only. No additional behavioral context is provided to resolve this discrepancy.

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 short but contains redundant text: 'FREE. (FREE)' appears at the end, which adds no value and looks like an error. The first sentence front-loads the purpose, but the repetition and lack of structured info about outputs detract from conciseness.

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

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

With no output schema, the description should explain what the tool returns (e.g., the watermarked image) but does not. It does mention robustness ('Survives light compression') and technical detail, but the annotation contradiction and missing return-value information leave the description incomplete for a tool that modifies an image.

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

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

Schema description coverage is 100%, so the baseline is 3. The description adds technical context (e.g., luminance channel, DCT-domain) that enriches understanding of the payload and strength parameters, but it does not provide significant new parameter-level details 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 embeds an invisible DCT-domain watermark into an image and encodes a text payload. This is a specific verb+resource+method, and it distinguishes from sibling tools like watermark_detect (which detects watermarks).

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 a use case via 'Survives light compression,' suggesting the tool is suitable when light compression robustness is needed. However, it does not explicitly state when to use this tool versus alternatives like watermark_detect, nor does it provide any exclusions or prerequisites.

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