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

With annotations only covering readOnlyHint=false and openWorldHint=false, the description adds substantial context the annotations cannot: ephemeral in-memory processing, no retention, masked findings persisted to a private scan record, no AI provider access, and a Pro-key requirement. This is exactly the kind of data-handling and auth disclosure an agent needs before sending source code.

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 core action is front-loaded in the first sentence, and the remaining sentences each carry a distinct fact (auth, retention/masking, provider isolation, language coverage, no-score outcome). The two adjacent privacy sentences overlap slightly and the block is dense, but nothing is padding.

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 one-parameter tool with no output schema and thin annotations, the description covers behavior, auth, data handling, and even hints at the result ('no score' when nothing is analysable). It does not describe the shape of the returned findings or where the scan record is surfaced, leaving a modest gap.

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% for the single 'files' array, so the description must compensate; it explains the semantic content (editor file contents, JS/TS analysed, other files secrets-only) but omits the structural constraints the agent will hit (max 50 files, 200k chars per content, path/content shape). Partial compensation, not full.

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 gives a specific verb and resource ('Send selected editor file contents to the SimplyScan Security Engine's deterministic repository rules') and pins the scope as local/editor code, which cleanly separates it from the sibling scan_website. An agent can identify the operation without opening the 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?

It states a real prerequisite ('Requires a Pro API key') and scopes applicability ('Code rules analyse JavaScript and TypeScript; other files are checked for secrets only'), which tells the agent what input is worth sending. It never explicitly contrasts itself with scan_website or states when not to use it, so it falls short of full routing guidance.

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