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

Beyond the annotations (readOnlyHint, openWorldHint, idempotentHint, destructiveHint), the description discloses that the audit is static, deterministic, and makes no LLM calls. It also states that it does not invent audits when data is missing. These are behavioral traits not covered by annotations, adding significant transparency.

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 compact and well-structured. It front-loads the core purpose in the first sentence, then adds operational details in subsequent sentences without redundancy. Every sentence contributes to the agent's ability to use the tool correctly.

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 that an output schema exists (so return values are defined elsewhere) and the annotations cover the safety profile, the description covers all necessary operational aspects: how to select between URL and snapshot, how to populate snapshot from client context, and what to do when data is missing. Nothing essential is omitted.

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?

The schema already documents all three parameters with 100% coverage, so the baseline is 3. The description adds extra meaning for the snapshot parameter: it explains how to obtain it from client context (using MCP 'name' or Cursor-style 'tool') and explicitly forbids using file paths or $ref. This goes beyond the schema's static description, so a 4 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?

The description clearly states the tool's purpose: to statically audit an MCP tool surface from a public HTTPS URL or a tools/list snapshot. It specifies the verb (audit), the resource (MCP tool surface), and the input sources, while also clarifying that it is static and does not invoke target tools or make LLM calls. This is specific and unambiguous.

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 explicit guidance on when to use a URL versus a snapshot, and how to handle requests to check another installed server: read its definitions from client context and pass them as snapshot. It also instructs what to do if definitions are unavailable (ask for the endpoint or JSON) and what to avoid (file paths, $ref). This is clear when-to/ when-not-to guidance with fallback behavior.

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