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

Annotations already declare readOnlyHint=true and openWorldHint=true, but the description adds material context beyond them: it opens a single connection, calls no tools, enumerates the specific scan classes performed, and discloses the decision enum returned. It stops short of stating latency or failure behavior when the endpoint is unreachable.

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?

One dense, front-loaded block that opens with cost and trigger, then enumerates capabilities, then the return value and inputs. Every clause contributes a distinct fact; nothing is restated from the title or schema.

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 and does so: it names the verdict values (allow, review, deny), the hash token, and the risky-tool listing. For a two-parameter read-only check tool, an agent has everything needed to decide to call it and how to read the result.

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%, so the baseline is 3. The description goes beyond the schema's terse 'Hash from an earlier check' by explaining the purpose of tools_sha256 — pass it next time to detect a changed tool list — which supplies the operational meaning the schema omits.

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?

States a specific verb and resource — connects once to an MCP server, scans its tool descriptions for injection wording and invisible characters, checks domain/publisher — plus the concrete output (allow/review/deny decision). It is unmistakably distinct from every sibling, which are all domain, company, address or sanctions lookups.

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?

Explicitly prescribes the trigger: 'Use before connecting to or installing an MCP server you have not used before, or to re-check one.' It also names the re-check path via tools_sha256, so both the first-use and repeat-use cases are covered.

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