Onchain Alpha Lab

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

With no annotations, the description must disclose behavioral traits. It only lists signal types but does not explain side effects, read-only nature, rate limits, or what happens with multiple parameters. Behavioral transparency is minimal.

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 17-word sentence, concise without redundancy. However, a more structured format (e.g., bullet points) could improve readability given the multiple parameters and signals.

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?

Despite having 4 parameters and no annotations, the description omits usage patterns and output expectations (though output schema exists). It does not cover how to use the tool for different inputs, making it incomplete for automated selection and 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?

Schema description coverage is 0%, yet the description only vaguely hints at token_address and candidates. It fails to explain 'focus', 'chain', or how parameters interact. Significant gap in parameter meaning.

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 'Analyze' and specifies the resources: token, contract, or candidate token lists. It lists covered signals (market, liquidity, etc.), differentiating it from sibling tools like analyze_x_content and generate_new_pool_report.

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. The description does not specify prerequisites, ideal scenarios, or exclusion criteria, leaving the agent to infer usage.

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 fully disclose behavioral traits. It does not mention authentication requirements, rate limits, data freshness, or any side effects. The output schema exists but is not described.

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, but overly long and lists multiple analysis goals. Could be more concise by separating core functionality from examples. Verb 'Analyze' is appropriately 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?

With 5 parameters (0 required) and an output schema, the description is incomplete. It doesn't explain how parameters combine (e.g., can items be used with topic?), or what the output format is. Agent missing critical usage context for effective 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?

Schema description coverage is 0%. The description vaguely maps to parameters (text->items, topics->topic, accounts->account) but does not clarify differences or constraints (e.g., whether items is a list of tweet IDs or text strings). Language parameter is mentioned but not explained.

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 analyzes Twitter/X content (text, accounts, topics, collections) for summary, sentiment, narrative, spread risk, and trading clues. It distinguishes from siblings like analyze_onchain_alpha (on-chain data) and distill_kol_history (KOL history).

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 siblings, or when not to use it. The description lists capabilities but does not provide usage context or prerequisites (e.g., account authentication).

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 present, so the description carries full burden. It mentions 'fetch and distill' but does not disclose potential side effects, rate limits, or what 'distill' entails (e.g., whether it mutates or is read-only). Minimal behavioral context is 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?

The description is concise with two sentences and no unnecessary words. However, it omits important details that could be added without significant bloat.

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?

While an output schema exists (not shown), the description fails to explain what the tool returns, how distillation works, or provide adequate context given the sibling tools and parameter complexity. The agent lacks sufficient information to reliably invoke the tool.

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 3 parameters with 0% description coverage, and the tool description adds no meaning to any parameter. In particular, 'direction' is ambiguous (sentiment?, chronological?) and 'max_tweets' is not explained, leaving an agent unable to correctly populate 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?

The description clearly states the tool fetches and distills historical original tweets for a specified user, using a verb and resource. However, it does not explicitly distinguish this tool from its siblings (e.g., analyze_x_content) by stating when to prefer it over alternatives.

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 by stating 'the buyer only needs to provide a username and distillation direction', but it provides no guidance on when not to use the tool or what alternatives exist.

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 fully disclose behavioral traits. It only states it generates a report, omitting whether the operation is read-only, any authentication needs, rate limits, or side effects. The term 'report generation' suggests read-only, but not explicitly stated.

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 clear sentence of 22 words, front-loading the purpose and data sources. However, it could benefit from a more structured format (e.g., bullet points for data sources) for easier parsing.

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?

While an output schema exists (reducing need to explain return values), the description still lacks coverage of parameter details and usage context. It does not explain what the report contains beyond the listed data sources, leaving gaps for a tool with 4 parameters.

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 0%, yet the description provides no details on individual parameters (token_address, chain, focus, time_window). It only broadly mentions data sources, leaving the agent to infer parameter meanings.

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 generates a review report for a new pool or breakout token, listing specific data sources (K-line, holders, social mentions, wallet behavior, score changes). It effectively distinguishes from sibling tools which focus on narrower analyses like on-chain or X content.

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 new pools/breakout tokens but gives no explicit guidance on when to use it versus alternatives such as analyze_onchain_alpha or analyze_x_content. No context on prerequisites or exclusions.

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