codesafe_audit_bug

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

With no annotations provided, the description carries the full burden of behavioral transparency. It explicitly states what the tool does (pulls rule definition, taint trace, sink context, reconstructs source→sink path) and what it does not do ('nothing is written to the platform'). This clearly sets expectations for a read-only, context-assembly tool, which is highly transparent for a tool with no annotation support.

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 a one-sentence summary at the start and clear elaboration. The final sentence ('Respond with a judgment...') is more of an instruction to the LLM than a description of tool behavior, but it does not add excessive bulk. Overall, it is well-structured and avoids unnecessary repetition.

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 description is complete for a tool of this complexity. It explains the purpose, what data is pulled, what is returned, and the read-only nature. An output schema exists (not shown) which the description references, so return values are covered. No annotations are present, but the description provides enough context for safe use. It could be considered 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?

Schema description coverage is 0%, so the description must compensate by explaining parameters. It does not. While parameter names (task_id, bug_id, context_lines) are somewhat self-explanatory, the description does not clarify their roles, how they relate to 'one defect', or the meaning of context_lines. This is a significant gap given the low schema coverage.

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 opens with a specific verb+resource: 'Assemble a judgment-ready audit context for one defect.' It clearly states what the tool does: pulls rule definition, taint dataflow trace, and sink code context, and returns them together with judging criteria and output schema. It distinguishes itself from siblings by combining these elements and explicitly noting that nothing is written to the platform, differentiating it from codesafe_submit_audit.

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 clear context on when to use the tool: to gather all necessary context for judging a single defect, with the verdict produced by the calling LLM. It also notes that nothing is written to the platform, implying it is for read-only analysis and not for submission. However, it does not explicitly name alternative tools or state 'use this instead of X', so it stops short of full alternative exclusions.

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