tariff.watch

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

The description mentions 'sandbox' implying some isolation, but it does not disclose security implications, permissions, or what happens if the command hangs. No annotations are provided to supplement this.

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 conveys the essential purpose and outputs. No unnecessary 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's simplicity and lack of output schema, the description is adequate but could include details on error handling, timeouts, or expected formats for stdout/stderr.

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 0% schema description coverage, the description adds context by explaining the command is a 'shell command' and listing returned values. However, it does not provide format, constraints, or examples for the parameter.

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 runs a shell command and returns stdout/stderr and exit code. However, it lacks differentiation from the sibling tool 'run_code', which might also execute code in a sandbox.

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 like 'run_code'. It does not specify prerequisites or scenarios where exec is appropriate.

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 mentions a 'persistent sandbox interpreter', implying statefulness and isolation, which is useful behavioral context. However, it lacks details about side effects, resource limits, termination guarantees, or security restrictions. Given no annotations, it carries partial burden but still insufficient.

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 (two sentences) and directly conveys the core purpose. It is front-loaded and avoids redundancy. However, it could be slightly more structured to include key behavioral notes.

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 code execution tool with two parameters, no output schema, and no annotations, the description is incomplete. It omits critical details like error handling, output format, execution timeouts, returned data structure, and state management across calls. The persistent sandbox feature adds significant context but is not elaborated.

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 0% schema description coverage, the description adds minimal value. It only clarifies the language parameter defaults to Python, but provides no semantics for the 'code' parameter (e.g., syntax, size limits, or execution model).

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 that the tool executes code in a persistent sandbox interpreter and returns output. It also mentions the default language (Python). However, it does not differentiate from the sibling tool 'exec', which may lead to confusion.

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 sibling 'exec' or any alternatives. It only mentions that Python is the default language, but does not specify prerequisites or suitable scenarios.

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