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

Annotations only declare readOnlyHint and openWorldHint; the description adds substantial context beyond them: it performs no tool calls, requires no key, records every first observation and change in an on-chain-anchored transparency log, and returns a grade plus public-history link. Destructive/exfiltration surface is explicitly ruled out, which is exactly the behavioral detail an agent needs before wiring up a remote endpoint.

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?

Front-loaded with the purpose and the read-only guarantee, and the verdict enumeration prevents ambiguity. It is dense but the comma-chained verdict list and trailing log/key clauses make it read as one long block rather than cleanly separated statements, leaving a little room for tightening.

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?

With no output schema, the description carries the return-value burden itself and does so: it names all six verdict outcomes and the tools_hash, A-F grade, and history link the caller receives. Combined with the schema's 100% coverage, 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 both url and expected_tools_hash are already documented, including the rug-pull semantics of the hash. The description reinforces expected_tools_hash meaning ('changed (tools differ from expected_tools_hash)') but adds no syntax, format, or default 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 precise verb+resource ('safety check for any remote MCP server') and immediately clarifies the mechanism ('reads the server's tool list ... never calls a tool'). It then enumerates the exact verdict set (ok, caution, danger, changed, unverified, unreachable), so an agent knows exactly what class of answer to expect 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?

Timing is explicit: 'before an agent connects to it or after it was approved.' That covers when to call, but it never names an alternative sibling (e.g. scan_server, scan_rescan, guard_check) or states when-not to use it, so the routing decision is left partly to inference.

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