autonomous-intelligence

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

With no annotations, the description carries the burden and does well: it discloses the 2% fee, the unsigned nature, API key requirement, and the privacy property that the key never leaves the environment. It could mention side effects or persistence of the build_id, but covers critical behavioral traits.

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 dense sentences front-load the purpose, then add the key operational details. There is no filler or redundant restatement of the tool name.

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 workflow context is helpful, but the tool lacks a concrete input schema, any parameter descriptions, and an output schema. The description only mentions build_id, leaving the unsigned transaction format and required args unspecified, which is insufficient for reliable invocation.

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 is a generic 'args' object with 0% property coverage, and the description gives no guidance on what fields to include (e.g., tokens, amount, slippage). An agent cannot construct a valid 'args' payload from the description alone.

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 identifies the action: 'Build an UNSIGNED swap transaction' with a concrete output 'a build_id'. It distinguishes itself from sibling submit_swap by emphasizing the unsigned, local-signing stage.

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 provides a clear workflow: requires an API key, sign locally with your own wallet, then call submit_swap with the same build_id. It does not explicitly name alternatives or exclusions, so it misses the top score.

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 of behavioral transparency. It lists what is checked but does not disclose whether the tool is read-only, what the return format is, or any limitations (e.g., it may not guarantee full safety). This leaves uncertainty about side effects and output.

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 front-loads the main verb and quickly lists the checks. It avoids unnecessary fluff, though it could be more structured to include parameter hints.

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 tool has no output schema and minimal schema, so the description must explain inputs, outputs, and context. It fails to state what parameter to provide, what the result looks like, or any caveats. For a safety-check tool, these gaps make it incomplete for an agent to 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 input schema is generic with a single 'args' object and no property definitions, and the description contains zero parameter information. With 0% schema coverage and no compensation in the description, the agent cannot infer what input is required (e.g., token address or symbol).

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 with a specific verb ('Rug-gate') and names four distinct safety checks: honeypot, mint/freeze authority, liquidity lock, and holder concentration. This distinguishes it from sibling tools like get_token_info or build_swap, which have different focuses.

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 is provided on when to use this tool versus alternatives. While it is implied this is a pre-trade safety check, the description does not explicitly state conditions, prerequisites, or mention any sibling tools as alternatives.

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 burden but does not explain behavior beyond the 'rug-gated' filter. It does not disclose return format, pagination, or what 'rug-gated' implies operationally.

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 very short and front-loaded, avoiding unnecessary words. The two fragments are concise, though the structure could be improved by making the 'tab' instruction a full sentence.

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 generic schema, lack of annotations, and no output schema, the description is incomplete. It only hints at a tab parameter and does not address how to invoke the tool fully or what results to expect.

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 is a generic 'args' object with no documented keys. The description adds meaning by specifying the 'tab' key and its allowed values ('new', 'trending', 'graduated'), which is valuable for a schema that otherwise provides no parameter details.

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 'Rug-gated new/trending tokens' which indicates a resource type but lacks an explicit verb like 'list' or 'find'. It does distinguish from sibling tools by focusing on rug-gated tokens, but the purpose is not clearly articulated beyond a noun phrase.

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 alternatives. It does not mention exclusions, prerequisites, or comparisons to sibling tools like list_tradeable_tokens or get_token_info.

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 discloses the 2% fee and the pieces of the quote (route, expected out), adding some behavioral context. However, with no annotations, it fails to state whether this is a read-only operation or if any state changes occur, leaving part of the behavioral profile untold.

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, front-loaded sentence with no filler. Every word adds value: 'Get a swap quote', the details of route/expected out/fee, and the input parameters.

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 quote tool, the description covers the core purpose and key inputs, but it lacks specification of the return structure or error behavior. With no output schema, some additional detail about the response format would make it more 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?

The input schema is a generic wrapper (args object with arbitrary properties) and has 0% coverage, but the description compensates by naming the required semantic inputs: inputMint, outputMint, and amount in base units. It doesn't give exact key names but provides essential meaning 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?

The description clearly states the tool's purpose: 'Get a swap quote' with specifics on the route, expected output, and 2% fee. It distinguishes itself from siblings like submit_swap by emphasizing the quote (non-execution) nature.

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 explicit guidance is provided on when to use this tool versus alternatives. It does not mention prerequisites, exclusions, or that it should be used before submit_swap, leaving the agent to infer usage 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 provided, the description carries the full burden of disclosure. It only states the data returned ('live price, liquidity and market cap') without mentioning input expectations, error behavior, data freshness limitations, or any other side effects. The term 'live' suggests real-time data but no further context is given.

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, front-loaded sentence that directly states the tool's purpose. It is concise with no wasted words, making it easy to parse quickly.

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 vague input schema (an arbitrary 'args' object) and the absence of an output schema, the description is insufficient. It does not explain what a 'mint' is, how to specify it, or what the response looks like. The tool is simple in concept, but the minimal description leaves critical gaps for an agent to invoke it 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 schema has a generic 'args' object with arbitrary properties and no parameter descriptions, so schema coverage is 0%. The description mentions 'a mint' but does not clarify the argument structure or key name needed. This leaves the agent to guess how to pass the mint identifier, providing only minimal compensation for the missing schema detail.

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 'Live price, liquidity and market cap for a mint' clearly indicates the tool returns these specific data points for a token mint. It is concise and distinguishes itself from siblings like get_quote by listing liquidity and market cap in addition to price, though it lacks an explicit verb.

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 is provided on when to use this tool versus alternatives like get_quote or check_token_safety. There is no mention of context, prerequisites, or exclusions, leaving the agent without direction on tool selection.

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, and the description provides no behavioral information such as pagination, sorting, rate limits, or whether it returns summaries or full details.

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?

Under-specified rather than concise; the single sentence provides almost no functional information.

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, no annotations, and a one-line description, the tool is severely under-documented for an agent to use effectively.

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 has an opaque 'args' object with no documented properties, and the description adds no parameter meaning. Schema coverage is 0%.

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 is a noun phrase defining what tradeable tokens are, rather than stating the action of listing them. It restates the tool name with slight elaboration ('swappable on the DEX') but lacks a verb and doesn't differentiate from sibling tools like get_token_info or find_gems.

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 tool vs alternatives. No exclusions or context provided.

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 were provided, so the description carries the full burden. It discloses that an API key is required and returns the signature and confirmation status, but does not mention side effects, irreversibility, failure modes, or rate limits. This is minimal but somewhat informative.

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 exactly two sentences, with the action front-loaded in the first sentence. Every word contributes value—no repetition, no filler, and no redundant restating of the tool name.

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 tool has no output schema, no annotations, and a vague parameter schema. The description does not explain how to construct the args beyond mentioning build_id, nor does it clarify what 'signature' and 'confirmation status' mean as return values, or whether the broadcast is synchronous. Thus it is incomplete for a tool that likely has important caveats.

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 provides zero descriptions for its single 'args' object, leaving it as a free-form container. The description only mentions 'build_id' but does not explain whether it is a top-level parameter or a key inside args, nor does it describe the expected structure of the args object. This is insufficient for a tool with such an opaque 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 uses a specific verb ('Broadcast'), identifies the resource ('already-signed swap transaction'), and specifies the key input ('build_id'). This clearly distinguishes it from sibling tools like build_swap, which presumably creates the transaction.

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 phrase 'already-signed' and 'with its build_id' clearly implies this tool is used after building and signing a swap, and that it requires a build_id. This provides clear context on when to use it, though it does not explicitly name alternatives or exclusions.

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