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

Annotations already declare readOnly/openWorld/idempotent/non-destructive, and the description adds substantial context beyond them: it never invokes the server's tools, requires public HTTPS endpoints, sends no credentials, and is rate-limited to a few checks per ten minutes. These are exactly the operational facts an agent needs before calling.

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 purpose and the 'use before adding an unknown server' directive are front-loaded, and no sentence is filler. The first sentence is long and heavily comma-listed, which costs some immediate readability, keeping it short of a 5.

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 two-parameter audit tool with no output schema, the description covers what is inspected, the safety profile, rate limits, and the local-server fallback. The enumeration of individual checks is deferred to an external URL, a minor gap for an agent that wants the full checklist inline.

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 coverage is 100% and both parameters (url, budget) are documented in the schema itself. The description only loosely connects to `budget` via 'what the list costs in tokens' and adds no syntax or format detail beyond the schema, so the baseline 3 applies.

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 states a specific verb and resource — read another MCP server's tool list and report issues such as tool poisoning, contradictory safety hints, undocumented parameters, and token cost. It is clearly distinct from siblings like compare_tools and get_tool, which operate on the already-known catalog rather than probing an unknown remote server.

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 gives explicit timing ('Use it before adding a server you don't know') and explicit exclusions with an alternative ('For local servers or ones that need a key, run anchor check on your own machine'). It also states access preconditions (HTTPS/public addresses, no credentials), which further scopes when this tool applies.

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