last_error

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

With no annotations, the description carries the full burden. It details behavior for different error types (runtime/syntax errors vs. security errors), explains the return value when there is no error, and mentions the excerpt length. However, it does not specify whether calling last_error resets or clears the stored error, which could be relevant. This minor gap prevents a perfect score.

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: four focused sentences that front-load the main purpose, then detail return types, edge cases, and usage advice. Every sentence adds essential information without redundancy, and the structure is logical.

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 simple nature (no parameters, no annotations) and the presence of an output schema (though not provided), the description fully covers the tool's behavior: what it returns for success/error cases, line number details, and usage context. No additional information seems necessary for an agent to correctly invoke this 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 zero parameters with 100% coverage, so the baseline is 4 per the rubric. The description does not need to add parameter information, and it adds value by explaining the return structure. There is no missing parameter information, hence a solid 4.

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: to return details of the last failed execute() call. It specifies the exact information returned (exception type, message, line number, excerpt) and differentiates itself from the sibling 'execute' tool by focusing on error retrieval. The verb 'Return' and resource 'details of the last failed execute() call' are specific and unambiguous.

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 explicitly advises when to use the tool: 'Call this immediately after an execute() error'. It also provides a reason for using it over alternatives: 'much faster than re-reading the submitted code'. This gives clear contextual guidance and implies that other methods (like reading code) are less efficient.

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