Submit a local file to VirusTotal

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

Beyond the annotations (destructiveHint=true, etc.), the description discloses non-confidentiality ('VirusTotal may share content'), absence of interactive confirmation, no retry behavior, durable reference for receipt recovery, and that local cancellation does not withdraw an accepted file. This adds substantial behavioral context not derivable from annotations alone.

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 front-loaded with the core action and then adds purpose-built caveats. Each sentence addresses a distinct concern (file type, confidentiality, retries, next steps, cancellation) without redundancy. It is appropriately sized for a tool with side effects and zero output schema.

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 no output schema, the description explains the post-submission lifecycle: the result is not a completion/verdict, and the agent should use get_submission/get_analysis. It covers operational requirements (quota, retries, durability) and side effects. The only minor omission is an explicit description of the return value shape, but the mention of a 'durable reference' and receipt recovery is sufficient in this context.

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 schema coverage at 0%, the description carries the full burden for parameter meaning. It explains path as a local regular file path (implying filesystem access) and expected_sha256 as an optional check that 'must match that copy.' It also adds the size limit, which is not in the schema. This fully compensates for the lack of schema descriptions.

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 states a specific verb ('Submit'), a resource ('one local regular file'), and a hard constraint ('at most 32000000 bytes'). It explicitly differentiates from sibling submit_file by stating 'Reads the local server's filesystem, never a remote client's path or a URL,' so an agent can distinguish local submission from remote/URL submission without inspecting schemas.

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 when-to-use and when-not-to-use guidance: it is for local server files only, never remote paths or URLs. It also gives operational context—uses current VTAI rights and quota, never retries a POST—and directs follow-up to get_submission and get_analysis, indicating the tool is not an endpoint for verdicts. This is explicit and complete.

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