Hugging Face

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

The description goes well beyond the readOnlyHint annotation, detailing specific behaviors: 'Cat reads confirmed UTF-8 text files only. It rejects repositories, directories, model weights, archives, images, media, Parquet, and other binary content.' It also discloses Attach's 4 MiB hard limit, file-extension-based classification, and Find's inherently recursive nature. 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 lengthy but well-structured, with clear sections for grammar, commands, and behavioral notes. While every sentence adds value, the sheer volume makes it less concise than optimal. The front-loaded purpose statement and organized layout earn it a high score, but the density prevents a perfect 5.

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 (six commands, many flags, URI types, and edge cases), the description is exceptionally complete. It covers all command semantics, filtering, sorting, binary file limitations, trending behavior, and points to hf://README.md for further details. With an output schema present, no critical context is missing.

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 only describes cmd and args generically. The description adds a complete grammar for each command, including flags like --recursive, --glob, --type, --sort, --limit, and specifics about URI formats, TYPE aliases, SORT options, and tokenization. This massively enriches parameter understanding far beyond the schema's 100% 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: 'Use to access the Hugging Face Hub. Navigate resources with ls, cat, attach, find, stat, and search over hf:// URIs.' It specifies the resource (Hugging Face Hub) and the verbs/commands available, distinguishing it from sibling tools like hf_whoami and hub_repo_search which are more specialized.

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

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

The description provides explicit usage guidance: 'Discover before access: use search, ls, or find to locate targets; use stat when target type is uncertain.' It also advises against unscoped find for global discovery and instructs to 'Omit --limit and --sort unless the request asks for a cap, ordering, or exhaustive results.' These are clear when-to-use and when-not-to-use directives.

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. The description adds valuable context by explicitly stating it is read-only and 'never returns credential values', providing a strong security guarantee. This goes beyond the annotations, though it partly repeats the read-only hint.

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, using two sentences to convey purpose, scope, and a key security property. Every word earns its place without 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?

Given the tool's simplicity (no parameters), the presence of an output schema, and clear annotations, the description adequately covers the essential contextual information. It explains what the tool does, its read-only nature, and credential safety, making it complete for an agent to select and invoke 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 tool has zero parameters, so the baseline is 4. The schema coverage is vacuously 100%, and the description correctly avoids inventing parameter details. No additional parameter explanation is needed.

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's function with a specific verb ('inspect') and resource ('Hugging Face authentication context'), listing the exact data covered (account, org memberships, credential access details). It distinguishes itself from sibling tools focused on file systems or repo 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?

The description clearly implies its purpose, but it does not explicitly state when to use this tool versus alternatives like hf_fs or hub_repo_details. No when-not-to-use guidance is provided, so usage context is 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 provide readOnlyHint=true and destructiveHint=false, and the description adds behavioral context by explaining auto-detection of repo type and the recommended ordering of dataset operations. 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 three sentences long, beginning with the core purpose and followed by targeted guidance for datasets. No redundant or filler content; each 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?

For a tool with 7 parameters and no output schema, the description covers the dataset workflow well, including discovery and preview conditions. It does not detail return shapes, but given the read-only nature and strong annotations, 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 covers 100% of parameters with descriptions, so baseline is 3. The description adds semantic value by linking operations to parameters (e.g., dataset_structure before dataset_preview, using config/split only when known), exceeding the schema's per-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 clearly states 'Get details for one or more Hugging Face repos (model, dataset, or space)' with a specific verb, resource, and scope. It differentiates from siblings like hub_repo_search by focusing on details retrieval and mentions auto-detection of repo type.

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 workflow for datasets: 'Use dataset_structure first to discover configs, splits, sizes, and schema. Use dataset_preview only when config and split are known.' This gives explicit context, though it does not mention when NOT to use the tool or direct alternatives among sibling tools.

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

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

The description adds context beyond the annotations by stating that the tool can aggregate across multiple repo types and that responses should include links to repositories. This is useful behavioral information, though it doesn't disclose details like rate limits or auth requirements, which are covered by 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 sentences, front-loaded with the verb and resource. The first sentence defines the tool, and the second elaborates on scope and response format. Every clause is purposeful, with no wasted words.

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

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

There is no output schema, but the description hints at the output by instructing the agent to include links to repositories. It covers the main capability (searching across repository types) and leaves parameter details to the schema. This is reasonably complete for a search tool, though it could mention sorting/limiting, which the schema already documents.

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 all 6 parameters with descriptions (100% coverage), so the baseline is 3. The description enhances the repo_types parameter by explaining the ability to target models, datasets, or spaces and aggregate across multiple types in one call, adding meaning beyond the schema's enum list.

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 'Search Hugging Face repositories' with a specific verb and resource. It also differentiates from siblings by mentioning targeting models, datasets, and spaces or aggregating across multiple repo types, 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 clear context that this tool is for searching across repo types and can aggregate multiple types in one call. It does not explicitly name alternatives or exclusions, but the context of a shared query interface and the sibling names (e.g., hub_repo_details) make the appropriate usage evident.

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