algo_check_plagiarism

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

With no annotations provided, the description must carry the burden of explaining behavior. It does disclose the core mechanism (token-level AST comparison) and top-level outputs, which implies a static, non-executing check. However, it does not define what 'verdict' means, what thresholds determine plagiarism, or what happens with incompatible inputs.

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 compact sentence that efficiently packs the action, method, and return values. There is no filler, and the most important information is 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?

Given the simplicity of this two-string-parameter tool, the description is largely complete: it explains what it analyzes, how it analyzes it, and what the output contains. Minor gaps remain around verdict semantics and language constraints, but they do not prevent a correct 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 100% because both codeA and codeB are described as 'code snippet'. The tool description adds no parameter-specific meaning beyond this, so it earns the baseline score of 3.

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 names a specific verb ('compares'), a clear resource ('two code submissions'), a method ('token-level AST analysis'), and the expected outputs ('similarity percentage and verdict'). This is instantly distinguishable from sibling tools like algo_run_sandboxed or security_scan_secrets.

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 intended use is reasonably clear from the description: use this when two code submissions need to be checked for similarity or plagiarism. However, it does not explicitly state when to use it over alternatives, what inputs are invalid (e.g., different languages), or any exclusions.

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