debridge-mcp

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

With no annotations provided, the description carries the full burden of behavioral disclosure but fails to explain critical execution details: whether this generates unsigned transaction data or executes immediately, what the return format is, failure modes, gas cost implications, or timing constraints for cross-chain settlement.

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 single-sentence description is perfectly efficient with zero waste. Each component earns its place: the verb ('Create'), the object ('cross-chain swap transaction'), and the protocol context ('via the deBridge DLN protocol').

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 complex 12-parameter financial transaction tool with no output schema or annotations, the description is insufficient. It omits critical context such as prerequisite steps, security considerations for cross-chain operations, slippage protection mechanisms, and what the tool returns (transaction payload vs. execution 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?

The input schema has 100% description coverage, establishing a baseline score of 3. The description adds no additional parameter context (e.g., explaining the relationship between authority addresses, or that dstChainTokenOutAmount accepts 'auto'), but meets the minimum threshold given the comprehensive 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 specific action (Create), resource (cross-chain swap transaction), and underlying protocol (deBridge DLN). It effectively distinguishes from the sibling tool 'transaction_same_chain_swap' by explicitly specifying 'cross-chain'.

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 the same-chain alternative, nor does it mention prerequisites such as token approvals, balance requirements, or the need for subsequent transaction signing/broadcasting.

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 carries full burden. Mentions returning a 'full guide' but omits format (markdown/plaintext), approximate length, structure, or whether content is static/dynamic. Adequate but minimal behavioral disclosure.

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 zero waste. Critical instruction 'CALL THIS FIRST' is appropriately front-loaded in all-caps for emphasis. 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?

Sufficient for a zero-parameter onboarding tool. Mention of 'full guide' provides adequate context despite missing output schema, though specifying return format (e.g., 'markdown guide') would strengthen 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?

Zero parameters present, warranting baseline score per rubric. Schema is empty object with 100% coverage. Description correctly implies no inputs are required.

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 specific verb ('Returns') and resource ('full guide') with clear scope. Distinct from siblings like get_supported_chains (which returns chain data) and create_tx (which creates transactions).

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?

Explicit instruction 'CALL THIS FIRST' establishes clear sequencing for onboarding. However, lacks explanation of why it should be called first or what specific information the guide provides that prerequisites other calls.

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 carries full disclosure burden. States scope 'all' (implying no filtering/pagination) but omits details about caching, rate limits, data freshness, or whether results are static versus dynamic.

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 sentence with zero waste. Essential information (action, resource, provider, context) is front-loaded and appropriately sized for a zero-parameter discovery tool.

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 low complexity tool (0 params, no annotations). Mentions return type implicitly via 'List', though could benefit from brief note on return structure since no output schema exists.

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?

Input schema contains zero parameters, triggering baseline score of 4 per evaluation rules. Description appropriately requires no additional parameter explanation.

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 specific verb 'List' with clear resource 'blockchain networks', specifies the provider 'deBridge', and scopes it to 'cross-chain swaps' context which distinguishes it from the sibling 'transaction_same_chain_swap' 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?

Provides implied usage context through 'for cross-chain swaps' phrase, but lacks explicit guidance on when to invoke (e.g., before using create_tx) versus alternatives or prerequisites for the workflow.

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 full disclosure burden. It identifies the data source ('deBridge token database') but fails to disclose behavioral traits like search logic (fuzzy vs. exact), rate limits, authentication requirements, or what happens when no matches are found.

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 redundant words. It front-loads the action and resource, earning 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?

For a 4-parameter search tool with simple types and no output schema, the description covers the basic function but leaves gaps. It does not clarify the relationship between 'query' (required) and 'name' (optional filter) parameters, nor does it hint at the return structure despite the lack of 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?

With 100% schema description coverage, the baseline is 3. The description lists searchable fields ('name, symbol, or contract address') which mirrors the 'query' parameter schema, but adds no additional semantics, examples, or clarification on how 'query' differs from the separate 'name' filter parameter, nor does it elaborate on expected formats for contract addresses.

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 specific action ('Search') and resource ('tokens') with the specific fields used for searching ('name, symbol, or contract address'). It implicitly distinguishes from transaction-focused siblings (create_tx, transaction_same_chain_swap) by being a database lookup, though it doesn't explicitly name them.

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 context by specifying searchable fields and the target database ('deBridge token database'), but lacks explicit when-to-use guidance or contrasts with alternatives. Since siblings perform fundamentally different operations (transactions vs. search), the lack of explicit comparison is acceptable but not ideal.

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 full disclosure burden but fails to clarify critical behavioral traits: whether the tool returns an unsigned transaction for client-side signing or submits directly, what the return value contains (transaction hash? serialized data?), failure modes, or gas estimation 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?

Single sentence is appropriately front-loaded with no redundant phrases. However, extreme brevity is insufficient for an 11-parameter financial operation tool where safety-critical context is missing.

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 complex mutation tool with no output schema and no annotations, the description omits essential context: return value structure, execution model (sign-and-send vs. build-only), and deBridge-specific behavioral constraints. The 100% schema coverage for inputs does not compensate for missing output and behavioral documentation.

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 parameters are fully documented in structured fields. The description adds no supplemental semantic context (e.g., address format expectations, 'auto' behavior semantics for slippage/amount, or relationships between affiliate fee parameters), warranting baseline score.

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 core action (create), resource (same-chain token swap transaction), and provider (deBridge). It effectively distinguishes from potential cross-chain operations via the 'same-chain' qualifier. However, it does not clarify relationship to sibling 'create_tx' (whether this is a specialized variant or distinct pattern).

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 provided on when to use this tool versus the generic 'create_tx' sibling, nor any mention of prerequisites such as token approvals, balance requirements, or supported chain validation that should precede invocation.

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