Submit inline file bytes to VirusTotal

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

Annotations already declare destructiveHint=true, openWorldHint=true, idempotentHint=false, so the safety bar is lower, yet the description adds substantial context beyond them: content is shared with the VirusTotal community and partners, bytes are visible to the MCP host/model, no tool-level confirmation is added, identity/quota carry over without credentials in arguments, and existing reports short-circuit a new analysis. This is exactly the extra behavioral disclosure annotations cannot express.

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 key technical constraint is front-loaded in sentence one, but the body is a dense run of fragments with overlapping ideas ('Never downloads a URL or interprets content as a filesystem path' vs. 'A remote server cannot read your local path') and no grouping between technical limits, confidentiality warnings, and recovery guidance. Most sentences earn their place, but the structure is loose for the amount of content.

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?

With no output schema, the description still tells the agent what comes back (existing reports without a new analysis, and an analysis ID to feed to get_analysis) plus size limits, confidentiality, and failure recovery. The response object's shape is not described, but the chaining information an agent needs to proceed is present.

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 carries the burden, and it partially does: it clarifies that content_base64 is decoded to at most 24,000,000 bytes (a tighter, decoded-size constraint vs. the schema's 32,000,000 maxLength) and that the sha256 must match those bytes. It never explains where the sha256 comes from, whether it is caller-computed, or the base64 canonicalization format, leaving real gaps for a 0%-coverage schema.

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?

States a specific verb and resource: submit canonical base64 bytes matching a SHA256, with a decoded size ceiling. It actively distinguishes itself from siblings by ruling out URL submission, path interpretation, and pointing larger files to a client with file-submission capability, so an agent can separate it from submit_url and submit_local_file without opening a schema.

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?

Explicit when-to-use (only on explicit user request), when-not (ask before sharing user documents, internal code, credentials, personal data, unfamiliar files), and alternatives/routing (get_submission for recovery, get_analysis for the returned analysis ID, a client-side capability for large files). Conditions are stated rather than implied.

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