toolsniff: scan an agent skill or MCP server before installing it

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

Goes well beyond the readOnly/openWorld/idempotent annotations: it describes the sandbox ('reads every file as text in a sandbox'), confirms it neither executes nor installs, warns that 'safe-looking' means only 'no rule matched', advises treating output as untrusted data, and adds latency bounds (2-15 s, up to 60 s) plus pricing/free-tier limits. This is unusually rich behavioral context.

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?

Purpose is front-loaded and almost every sentence carries actionable information (alternative routing, limitations, timing, cost). It is dense and long, with pricing/free-tier and docs-link content that borders on non-essential, but nothing is redundant with structured fields in a wasteful way.

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?

For a scan tool with an output schema already present, the description still adds value by naming the verdict/risk_score/findings shape and enumerating the finding categories. Combined with limitations, non-execution guarantees, timing, and cost, an agent has everything needed to decide and call correctly.

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%, so the schema already documents source, filename, and content_base64 formats in detail. The description adds no parameter-level detail (e.g. no syntax hints or source/content mutual-exclusion note) beyond what the schema provides, so the baseline 3 is appropriate.

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 ('Scan an AI-agent skill or MCP server package before installing it') and immediately distinguishes itself from the sibling check_mcp_server by naming the alternative and its purpose. An agent can tell exactly what this does and how it differs from the reachability-checking sibling.

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?

Gives an explicit usage condition ('before installing it'), names the alternative tool with the condition that selects it ('To see whether a remote MCP server answers use check_mcp_server'), and enumerates the cases where it will not help (dynamic tool registration, runtime downloads, nested archives, obfuscated logic). When/when-not/alternative are all present.

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