AIMALL (搜蚁智选)

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

With no annotations provided, the description carries the full burden. It discloses a key behavioral trait: '在不扣费的情况下' (without charging), informing the agent this operation does not incur cost. It also uses '预估' (estimate), implying it does not execute an API call. These are valuable, non-obvious behaviors beyond what the schema shows. It doesn't address response format, but core safety aspects are covered.

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

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

The description is two short sentences, immediately stating the primary action and cost nuance, followed by the usage context. Every word earns its place; there is no ambiguity. The transparency about non-charging is front-loaded. This is highly concise yet complete for the tool's scope.

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 of this simplicity (3 parameters, no nested objects) and no output schema, the description provides adequate operational context: it states the tool's exact purpose, the key behavioral guarantee (no deduction), and a concrete invocation scenario (budget gate). It could mention expected return value (USD number), but the description already says '费用（USD）' which strongly implies a USD amount. Overall, it suffices.

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 input schema already documents all three parameters (prompt, asset_id, max_tokens) with adequate descriptions. The tool description adds no parameter semantics beyond pointing to the estimate context. Per the baseline rule, when schema covers everything, a 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 verb and resource: '预估一次 AI 调用的费用（USD）' (estimate the cost of one AI call in USD). It also distinguishes itself from siblings by clarifying it is a budget gate ('预算闸门'), positioning it against ai_request which likely executes calls. This is specific 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 explicitly says '调用前用它做预算闸门' (use it as a budget gate before calling), which gives a clear when-to-use context. It does not explicitly name ai_request as an alternative, but the '调用前' (before calling) implies the intended counterpart. The guidance is strong though not fully exhaustive.

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 behavioral context beyond the raw schema: it is billed by usage, and the invocation returns a result, order number, and remaining balance. However, with no annotations provided, it does not go far enough to disclose possible side effects when calling a 'tool' asset, authentication requirements, failure modes, or cost limits.

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, efficient sentence with no filler and front- loads the most important information: what the tool invokes, that it is metered, and what it returns. It is not overly long, but it also doesn't use any paragraph or bullet structure to help with longer usage guidance.

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 five parameters, no annotations, and no output schema, the description still gives a helpful one-line summary of the return values (result, order number, balance). Yet it leaves out important context like what happens for tool-type assets, whether the call is async, and what error or cost-related details are returned.

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 all five parameters already have meaningful descriptions in the input schema. The tool description does not add any additional semantic detail about parameters, 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 a specific verb ('调用') and a specific resource ('AI 资产'), and clarifies the two possible variants: LLM conversation or tool. It clearly distinguishes itself from list_assets/get_onboarding/bootstrap_account by saying it actually invokes the asset and bills for it, though it does not explicitly state how it differs from ai_estimate.

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

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

There is no explicit guidance on when to use this tool versus its sibling ai_estimate or list_assets. The description says what the tool does, but it never states the prerequisite workflow ('get asset_id from list_assets first') nor that ai_estimate should be used for cost estimation before a request.

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 behavioral burden. It explicitly warns that 会创建真实账号 and states the tool returns a usable API Key, disclosing the key side effect. It doesn't cover duplicate-call consequences or reversibility, but the core behavioral risk is disclosed.

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

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

The description is a single compact sentence that front-loads the main purpose, states the key side effect, and gives the usage condition. Every clause earns its place, and no extraneous information is present.

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 string parameters and no output schema, the description covers purpose, return value, side effect, and usage timing. It lacks a detailed response format, but since it states that an API Key is returned, an agent can act reasonably without further detail.

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 describes email, password, and username. The description adds no parameter-specific detail beyond what the schema provides, so the baseline of 3 is appropriate.

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

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

The description clearly states the tool's action: self-register an account, create an Agent, and return a usable API Key. This is a distinct resource and purpose that stands apart from siblings like ai_estimate, ai_request, get_onboarding, and list_assets, so an agent can easily identify what it is for.

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 marks the tool as optional and says 仅首次接入时使用, giving a clear condition of when to use it. It does not name alternative tools or describe when not to use it, but the first-use gate is concrete enough for an agent to choose this only during onboarding.

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 burden of behavioral disclosure. It states the tool returns a guide and documentation link, but it does not mention whether this is a static payload, a network-looking operation, or whether any state is affected. For a zero-parameter getter this is acceptable but not deeply transparent.

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

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

The description is a single sentence with no filler or redundancy. It is front-loaded with the verb and subject, making the tool's purpose immediately clear.

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 parameterless tool, the description is nearly complete: it names both the onboarding guide and the machine-readable documentation link. Since there is no output schema, a bit more detail on the response shape could be helpful, but it is not strictly necessary for this simple use case.

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

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

The input schema has no parameters, so there is nothing for the description to add beyond what the schema already shows. The baseline of 4 is appropriate: with no parameters and 100% schema coverage, no parameter information is missing.

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

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

The description uses a specific verb, 返回/returns, and names an exact resource: the 搜蚁智选 onboarding guide and machine-readable documentation link. It clearly defines the tool's purpose and is distinct from the sibling tools, which all concern estimation, requests, or asset listing.

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 that this tool should be used when onboarding documentation for 搜蚁智选 is needed, but it does not explicitly state when to use it versus alternatives or mention any exclusion cases. The guidance is therefore implied rather than spelled out.

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?

There are no annotations, so the description carries the transparency burden. It discloses that the tool returns available market assets with their IDs, types, and prices, and the verb 'list' implies a read-only action. It does not discuss pagination, market scope, or authentication, but for a lightweight listing tool this is reasonably transparent.

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

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

The description is two short sentences with no filler. It front-loads the tool's core purpose and output, then adds a clear workflow instruction. 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 simple, optional-parameter listing tool, the description covers the key workflow, the purpose, and the main returned fields. It does not include an output schema, so a slightly richer statement about the list response could help, but the agent has enough context to call this tool correctly and proceed to asset_id-based calls.

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 only parameter, api_type, is fully documented in the schema with an enum and a description ('filter by type, empty returns all'), so schema coverage is 100%. The description adds little parameter-specific meaning beyond what the schema already provides, so the baseline score of 3 is appropriate.

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

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

The description names the specific resource (AI assets in the market) and the action (list), and explicitly lists the important returned fields (asset_id, type, unit price). It also clarifies its role in the workflow — 'use it first to find the asset_id to call' — which distinguishes it from sibling tools like ai_request or ai_estimate.

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 an explicit usage cue: use this tool first to obtain the asset_id needed for later calls. It does not explicitly name alternatives or say when not to use it, but the guidance is sufficient for a simple discovery step before the sibling request tools.

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