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

No annotations are provided, so the description carries the full behavioral burden. It does not disclose whether an existing file at savePath is overwritten, whether the parent directory must exist, required auth, or rate/ size limits — all relevant for a file-download mutation.

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

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

A single short sentence with the action front-loaded and no wasted wording. It is efficient, though it carries no structural elaboration such as caveats or return behavior.

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

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

For a simple 2-parameter tool with no output schema and full schema coverage, the description is barely adequate. It omits the behavioral details (overwrite, directory existence, failure modes) that matter when no annotations exist.

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 both 'url' and 'savePath' are already documented in the schema, including the 'absolute path incl. filename' constraint. The description adds no extra format or semantics beyond that baseline.

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

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

States a specific verb (下载/download) and resource (任务结果文件/task result file) plus the destination (本地指定路径). It clearly reads as the counterpart to runninghub_upload_file among the siblings, though it does not explicitly name any sibling.

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

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

No guidance on when to use this versus alternatives, no prerequisites, and no mention of what must happen first (e.g. that a task must have produced a result URL). Usage is only inferable from the tool name and the '任务结果' qualifier.

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

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

No annotations, so the description carries the full burden. It doesn't disclose read-only safety, pagination behavior (despite limit default 40), rate limits, or authentication needs. 'Browse' weakly implies a read, but no behavioral traits beyond the schema are provided.

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 short sentences, front-loaded with the core action. The second sentence duplicates the category enum from the schema, so it doesn't fully earn its place, but there's no filler text.

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

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

With no annotations and no output schema, the definition should do more to explain what is returned, how pagination works, and when to choose this over search_models. The description leaves those gaps.

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

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

Schema description coverage is 100%, so the baseline is 3. The description repeats the category enum already defined in the schema and adds no semantics for group or limit.

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?

States a specific verb (browse) and resource (RunningHub model catalog) scoped by category. It implicitly contrasts with search_models by emphasizing category browsing, but never names the sibling or the query-based alternative.

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 no when-to-use guidance, no exclusions, and does not mention the sibling runninghub_search_models. The only routing signal is the word 'browse', leaving the agent to infer that this is for enumeration rather than keyword search.

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

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

With no annotations, the description carries the full burden. It discloses the key behavioral trait that this is a single, non-blocking query, but says nothing about auth/permission requirements, rate limits, what happens when the task is still running, or result availability.

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 short, front-loaded sentences with zero filler; the core purpose comes first and the version distinction follows immediately.

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?

Adequate for a 2-parameter query tool whose params are fully documented, but with no output schema and no annotations, the description should say more about what is returned and the behavior when a task is incomplete.

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 both parameters (taskId, apiVersion) are already documented in the schema, including the fallback advice for apiVersion. The description merely restates the version split at a higher level, adding no syntax or format detail 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?

States a specific verb+resource: querying RunningHub task status and results, with the parenthetical '单次查询' clarifying it is a one-shot poll rather than a blocking wait. It implicitly distinguishes from runninghub_wait_task, though it never names that sibling.

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?

Gives when-to-use guidance for the two apiVersion values (standard model tasks vs workflow/AI app tasks), which is useful selection context. However, it offers no guidance on choosing this tool over runninghub_wait_task or runninghub_submit_task, so tool-level routing is only implied by '单次查询'.

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

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

No annotations are provided, so the description carries the full behavioral burden. It implies a safe read operation and discloses the return content (endpoints plus descriptions) and a filterable catalog size, but says nothing about pagination behavior, ordering, or result caps beyond the limit 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?

Front-loads the core purpose and catalog scale, then the category legend, then the next-step tool. Every sentence is functional, though the category enumeration could arguably live in the enum 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?

With no output schema, the description must convey the return shape, and '返回可用的 endpoint 与说明' is minimal — enough to know endpoints come back, but not the result structure or ordering. It covers the essential next step but leaves gaps an agent would need to probe.

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

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

Schema description coverage is 100%, so the baseline is 3. The description does add value by glossing the category enum (image=图像、video=视频、audio=音频、other=其他), but it adds nothing for keyword, group, or limit beyond what the schema already documents.

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?

States a specific verb (搜索) and resource (模型目录), plus scope details (350+ 标准模型 API 端点) and what is returned (endpoint 与说明). However it never distinguishes itself from the sibling runninghub_list_models, which an agent could easily confuse with a search 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?

The tool-to-tool handoff is explicit — 找到模型后用 runninghub_submit_task 提交任务 — which is genuinely useful routing. But there is no guidance on when to use this versus runninghub_list_models, nor any exclusion conditions, so the core selection decision is left to inference.

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

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

No annotations exist, so the description carries the full burden, and it delivers the key non-obvious facts: the call returns a taskId (asynchronous), results must be awaited via runninghub_wait_task, and the standard model API requires an enterprise-shared API Key. It still omits failure/error semantics and any rate-limit or quota 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?

Four compact sentences, front-loaded with the action, followed by workflow, return value, and the auth caveat. No sentence is redundant and nothing is buried.

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 4-parameter submission tool with no annotations and no output schema, the description covers the action, the required inputs' provenance, the return value, and the auth constraint. Minor gaps remain around error handling and what wait=true actually blocks on, which the schema only partially clarifies.

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

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

Schema coverage is 100%, so the baseline is 3, but the description adds real meaning: endpoint must come from runninghub_search_models, and params must contain exactly the fields the target model's documentation requires (and excludes auth info). That is guidance the schema alone does not provide.

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 names a specific verb+resource ('提交 RunningHub 标准模型任务') and scopes it to 'standard model' tasks, which distinguishes it from sibling query/wait/file tools. An agent can tell what this does without opening the 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?

It gives an explicit ordered workflow: call runninghub_search_models first to obtain the endpoint, then populate params from that model's docs, then use runninghub_wait_task for results. Alternatives and prerequisites are named rather than 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?

With no annotations provided, the description carries the full behavioral burden. It usefully discloses the return value (fileName) and the downstream wiring into fieldValue, but says nothing about size/format limits, overwrite behavior, authentication needs, or failure modes for an upload (a write) operation.

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 tightly written sentences with no waste, front-loading the action and return value before the downstream integration hint. 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?

For a single-parameter tool with no output schema and no annotations, the description covers what it does, what it returns, and how the result is consumed. It falls short of full completeness only on operational limits and error behavior.

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 there is only one parameter, so the schema already documents filePath as an absolute local path. The description adds only the broad category of accepted file types, which is marginal beyond the structured field, so the 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 states a specific verb (上传/upload) and resource (本地文件 - local image/video/audio/archive), and explicitly names the return value (fileName). It also distinguishes itself from the sibling runninghub_download_file by scoping to local-file-to-server direction.

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 gives clear usage context: upload first, then place the returned fileName into fieldValue for workflow/AI app image, audio, and video node parameters. However, it does not explicitly name alternatives (e.g., download_file) or state exclusions such as file-size or format limits.

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

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

With no annotations, the description carries the full burden and does disclose useful traits: the polling cadence, the terminal states (SUCCESS/FAILED), the timeout bound, and the return shape (URL list). It omits what happens on timeout (error vs partial result) and any auth/quota requirements.

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 tight sentences: the first front-loads the polling/wait behavior and termination conditions, the second states the return value. No filler.

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

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

No output schema exists, so the description correctly supplies the return shape (list of result file URLs). Combined with 100% schema coverage and the disclosed polling/timeout behavior, an agent has what it needs; only timeout-failure semantics are 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?

Schema coverage is 100%, and the schema itself richly documents apiVersion (with endpoints and fallback advice), timeoutSec, and intervalSec. The description only echoes the 5-second interval, adding no meaning beyond the structured fields, so the 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 gives a specific verb (poll/wait) and resource (RunningHub task) plus the completion condition. It implicitly separates itself from the single-shot runninghub_query_task by describing polling-until-terminal-state, though it never names that sibling.

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 only implied: an agent infers it should call this when it wants to block until completion. There is no explicit statement of when to prefer this over runninghub_query_task, and no exclusions or prerequisites.

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