agent

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

With no annotations, the description carries full burden. It discloses the non-custodial nature, the multi-step plan, and that the tool does not broadcast. However, it does not describe failure modes, permissions, or what the returned plan contains.

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

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

A single sentence that is front-loaded with the key purpose. Every word adds value; no redundancy.

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

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

Given 6 parameters, 5 required, no output schema, and no annotations, the description covers the basic flow but omits return value, error handling, or how to execute the plan. Sibling tools imply a quoting step, but this is not mentioned.

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

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

Schema description coverage is 100%, so baseline is 3. The description adds no per-parameter context beyond the schema's own descriptions; it only explains the overall flow.

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 'build a plan', the resource 'LP deposit', and the specific flow (approve → Permit2 sign → router.depositAnyToken). It distinguishes from sibling tools like build_lp_withdraw and build_swap by naming 'any-token LP deposit'.

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 notes 'No broadcast' and that the caller must sign and broadcast, but does not explicitly state when to use this tool versus alternatives (e.g., quote_lp_deposit first). No prerequisites or exclusions are given.

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

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

With no annotations, the description carries the burden. It reveals the plan is non-custodial and outlines the steps, but does not disclose potential side effects, permission requirements, or plan lifecycle. The 'No broadcast' line clarifies the tool does not execute transactions.

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 that packs key information (non-custodial, steps, no broadcast) without wasted words. It is front-loaded and to the point.

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 lacks explicit mention of the return format or data structure, which is important since there is no output schema. It hints at a 'plan' but leaves ambiguity about its contents. For a tool with 6 parameters and 5 required, more detail on output would improve 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 the schema already documents all parameters. The description adds no extra meaning beyond the schema's property descriptions, resulting in 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 'Build' and the resource 'NON-CUSTODIAL any-token LP withdraw plan'. It outlines the specific steps (approve shares → Permit2 sign → router.withdrawAnyToken), distinguishing it from siblings like build_lp_deposit (deposit) and build_swap (swap).

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

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

The description implies when to use this tool (for building a withdrawal plan) and states it does not broadcast ('No broadcast'). However, it does not explicitly exclude scenarios or mention alternatives, though the sibling list provides 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?

With no annotations, the description carries full burden. It discloses the multi-step plan and non-custodial nature, but does not describe output format (e.g., what signing means, returned object shape), error conditions, or gas/fee implications.

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

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

Two sentences with no wasted words. The most critical information is front-loaded: purpose and non-execution constraint.

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 complexity of a swap plan, the description lacks output schema details and does not connect to sibling tools (e.g., should quote_swap be called first?). The 100% schema coverage compensates, but output remains unclear.

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 parameter descriptions are sufficient. The description adds context about the overall plan but does not enhance individual parameter meaning 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 it builds a NON-CUSTODIAL ERC20 swap plan, outlines the steps (approve, Permit2 sign, router.swap), and specifies 'No broadcast,' which distinguishes it from transaction execution tools and siblings like quote_swap.

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 is for plan creation only, but does not explicitly state when to use it versus alternatives like quote_swap (for quotes) or other build_* tools. No direct guidance on prerequisites or ordering.

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 must cover behavioral traits fully. It only states the data is public and does not mention potential side effects, rate limits, error handling, or the format of the returned list. The description is too sparse for a safe read 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?

The description is concise, consisting of two sentences with no waste. It front-loads the key action ('List the public swap token allow-list') but lacks structured formatting like bullet points.

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 lack of output schema, the description partially explains the return fields (address/symbol/name/decimals). However, it omits details on list ordering, pagination (if any), error conditions, and behavior for invalid chainId. The tool is simple but could benefit from more 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% for the single optional parameter chainId, which already has a clear description. The tool description adds no additional meaning beyond the schema, so 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 clearly states the tool lists the public swap token allow-list with fields like address, symbol, name, decimals. It specifies 'public market data only,' which distinguishes it from private-read tools. However, it does not explicitly differentiate from sibling tools like list_vaults, but the domain is unique.

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 fetching public token data and explicitly states no user-private reads. However, it does not provide guidance on when to use this tool versus alternatives like list_vaults, nor does it mention prerequisites or exclusions.

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 provided, so description must fully disclose behavior. It mentions no private reads, but does not confirm read-only nature, rate limits, error handling for invalid chainId, or data freshness. The description is minimal, leaving the agent with gaps.

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

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

Two sentences, no redundant words. The first sentence states the main function, the second clarifies the scope. Efficiently front-loaded.

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

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

For a simple listing tool with one optional parameter and no output schema, the description covers what is listed and the scope. It could mention that output includes addresses and token pairs, but is largely complete without requiring additional 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 coverage is 100%, with chainId described as 'Defaults to mainnet (1)'. The description adds no extra parameter info beyond 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?

Description clearly states 'List the public any-token LP vaults (addresses + token pair)', identifying the verb (list), resource (vaults), and specific scope (public, any-token, LP vaults). This distinguishes it from sibling tools like build_lp_deposit and quote_swap, which are transactional.

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?

Description explicitly notes 'Public market data only — no user-private reads', guiding the agent to use this for public data and avoid when private vaults are needed. While no alternative is named, the sibling list does not include a similar list tool, so the guidance is sufficient.

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?

Without annotations, the description fully discloses behavior: returns 'pong'. No side effects are implied, which is appropriate for a health check. It could mention timeout handling, but it's sufficient.

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?

Extremely concise: two short sentences convey complete meaning 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?

Given zero parameters, no output schema, and a simple function, the description fully covers the tool's operation and expected result.

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?

No parameters exist; schema coverage is 100%. Baseline of 4 applies as no additional parameter info 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 states it is a health check that returns 'pong'. The verb 'health check' and expected output are specific. Sibling tools are complex operations, making this distinct.

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 implicitly indicates use for connectivity verification. No alternative tools exist for this purpose, so explicit when-not is unnecessary.

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?

Explicitly states 'Read-only' and 'No broadcast', making non-mutating nature clear. Lists outputs. However, no error handling or idempotency details. With no annotations, description carries full burden and handles it well.

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?

Single, compact sentence with no fluff. Efficiently conveys purpose and key 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?

Lacks output schema, so description should elaborate on return structure. Mentions output fields briefly but no format or example. Adequate for a preview tool but not fully complete.

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

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

Schema descriptions cover 100% of parameters adequately. Description adds minimal extra meaning (e.g., 'any-token' for inputToken is already implied). Baseline 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?

Description clearly states it's a read-only preview for LP deposits, listing specific outputs (estimated shares, minShares, fee, refund bps). Distinguishes from siblings like build_lp_deposit (broadcast) and quote_lp_withdraw (withdrawal).

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?

Implied usage for estimating deposit before broadcasting, but no explicit when-to-use, when-not-to-use, or alternatives mentioned. Sibling names provide context but description itself lacks explicit 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?

With no annotations provided, the description bears full burden for behavioral disclosure. It explicitly states 'Read-only' and 'No broadcast', which clearly conveys that the tool does not modify state. This is a strong safety signal, though it could mention additional traits like rate limits or authorization 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?

The description is exceptionally concise: a single front-loaded sentence followed by a short standalone phrase. Every word serves a purpose, and the key information (read-only, preview, estimated/guaranteed, no broadcast) is presented 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?

Given the complexity of 6 parameters, no output schema, and no annotations, the description is minimally adequate. It explains the core function and safety but lacks details on output format, error handling, optional parameters, or constraints (e.g., chainId restrictions). The agent may need additional context 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%, so the baseline is 3. The tool description adds no additional meaning beyond the schema; it does not elaborate on parameter roles, defaults, or relationships. The schema descriptions are adequate, but no extra value is contributed.

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 'Read-only any-token LP withdraw preview' with the verb 'preview' and resource 'LP withdraw'. It specifies the function as computing 'estimated and guaranteed token-out for burning vault shares' and adds 'No broadcast' to confirm no side effects. This differentiates it from siblings like 'quote_lp_deposit' and 'build_lp_withdraw' by emphasizing read-only preview.

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 previewing a withdraw without broadcasting, but it does not explicitly state when to use this tool versus alternatives like 'quote_lp_deposit' or 'build_lp_withdraw'. No exclusions or comparative guidance are provided, leaving the agent to infer 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?

No annotations provided, so description bears full burden. It accurately discloses read-only behavior and lists return fields. No contradictions.

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?

Extremely concise single sentence with key purpose and outputs. Front-loaded with 'Read-only ERC20 swap quote.' 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 no output schema, the description gives a high-level overview of return values but lacks precise types or structure. However, it covers the tool's purpose and key constraints adequately.

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 baseline is 3. Description adds no extra meaning beyond schema for parameters; it only summarizes outputs, which are not parameters.

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 it's a read-only ERC20 swap quote, specifying expected outputs (expected out, minOut, fee, route summary) and explicitly says 'No broadcast.'

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?

While it says 'No broadcast,' indicating it's for quoting only, it doesn't explicitly mention when to use this vs siblings like build_swap or other quote tools. However, the read-only nature is clear.

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