Hive Tax Observer

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

Discloses that it's observational only and shares rules with tax.classify. No annotations provided, so description covers core behavioral traits. Could mention idempotency or error handling, but adequate.

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 well-structured sentences. No redundant words. Front-loaded with action and key details.

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, description mentions return type (per-tx classification + by-kind summary). Covers limit (50) and constraints. Omits output format details, but sufficient for an agent to infer.

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 0%, but parameter names (tx_hashes, chain) are self-explanatory. Description adds context that tx_hashes refer to transactions and chain is likely blockchain. However, no further detail on valid values or format beyond enum.

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?

Clearly states it classifies an array of transactions in a single call (max 50), with per-transaction and summary results. Distinguishes from sibling tax.classify by noting same hard rules but bulk operation.

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?

Explicitly says 'observational data only, no advice, no filing, no cost basis computation', which tells when not to use. Implies use for bulk classification while tax.classify for single. Also mentions max 50 constraint.

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 fully bears the burden of transparency. It discloses that the tool performs real on-chain reads, classifies events, and surfaces specific inputs, while explicitly stating it does not compute cost basis or provide tax advice. This is comprehensive for a read-only classification tool.

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 four sentences, each adding distinct value: purpose, outputs, limitations, and supported chains. It is front-loaded with the core action and avoids redundancy, making it highly concise and well-structured.

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 lacking an output schema, the description lists the specific fields returned (holder, asset, amount, counterparty, timestamp) and states limitations. This provides sufficient context for an AI agent to understand the tool's outputs and constraints, making it complete for its complexity.

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 already covers both parameters (chain and tx_hash) with full descriptions, including enum values for chain. The description adds no additional meaning or clarification beyond the schema, so a 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 classifies a single on-chain transaction as a taxable event, listing specific event types (sale/swap/income/transfer). It also mentions what the tool surfaces (cost-basis-relevant inputs) and what it does not do, distinguishing it from siblings like tax.bulk (which likely handles multiple 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?

The description implies usage for a single transaction by stating 'single on-chain transaction' and listing supported chains. It also explicitly states what Hive does not do, but does not directly compare to siblings tax.bulk or tax.today, missing clear when-to-use 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, the description carries the burden. It explicitly states the tool is free and provides a count of classified events broken down by kind, which is a read-only operation. No contradictions or hidden behaviors.

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 conveys all necessary information 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 the tool has no parameters and no output schema, the description is complete. It explains exactly what the tool returns (counts by kind with a subtotal) and its time range.

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 the description does not need to add parameter information. Baseline 4 is appropriate given zero 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 returns a count of classified events in the last 24 hours, broken down by kind (sale/swap/income/transfer) with a taxable-signal subtotal. It differentiates from siblings by focusing on a daily summary.

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 a quick daily summary but provides no explicit guidance on when to use this tool versus siblings like tax.bulk or tax.classify, nor any exclusions.

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