Audit a live MCP server

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

Annotations already declare readOnlyHint=false (consistent with spawning a process), openWorldHint=true, and destructiveHint=false, so the safety profile is largely covered. The description adds real value on top: it discloses that a server process is launched, that the tool compares against the previous inspection (implying persisted state), and that it flags poisoned descriptions and missing destructiveHint - details the annotations cannot convey. It stays silent on network/auth implications of the open world.

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?

A single front-loaded sentence with the action first and the audit dimensions collected in a colon list - no filler and no redundancy. Slightly dense, but every clause adds a distinct capability rather than restating the name.

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?

An output schema exists, so the return shape needn't be explained, and the description covers inputs, the act of inspection, and the categories of findings. The only residual gap is the statefulness implied by 'changed since the last inspection' - where that baseline is stored and whether it must be primed - which is left unstated.

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 command, args, and url are already documented in the schema. The description reinforces the two input modes (stdio command vs Streamable HTTP url) and mirrors the schema's own example, but adds no syntax or format detail beyond it. Baseline 3 applies when the schema carries the parameter documentation.

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 names a concrete verb and resource: it starts an MCP server (stdio command or Streamable HTTP url), reads its tool list, and audits it. It even enumerates the audit dimensions, so the agent knows exactly what output to expect. What it lacks is differentiation from the sibling check_server or audit_config - the reader can't tell from the text alone which of these to reach for.

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 mechanics of use are implied clearly (start the server either via a stdio command or a URL, then audit), but there is no explicit when-to-use, when-not-to-use, or pointer to the alternatives among audit_config, check_server, and scan_config. Given three similarly-named siblings, the routing burden is left to inference.

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