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

Annotations only declare readOnly/idempotent/openWorld/non-destructive, and the description adds substantial operational context on top: up to four tools/list pages, no tool calls or redirects, a failed probe or index is not charged, no-match returns count 0 at the route price and is not proof of absence, the endpoint host is disclosed to Smithery's public search, and returned page text is untrusted data. Latency bounds (1-8 s typical, ~25 s max) and pricing (USD 0.01, no free allowance) are stated explicitly.

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 purpose and then pricing, limits, safety and privacy in a compact telegraphic style with essentially no filler. The only waste is the redundant "agentscan:" prefix that duplicates the title, and the clipped sentences cost a little readability.

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 an output schema present, return-value explanation is unnecessary, and the description still covers the cost model, free-allowance absence, page cap, timeout ceiling, probe-failure billing, null semantics, and prompt-injection caution. Nothing material for correct invocation or interpretation of results is missing.

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 the schema already spells out the https streamable-HTTP/legacy-SSE constraint, port 443 and no user info, so the baseline is 3. The description nevertheless adds meaning beyond the schema by stating the public-endpoint/no-credentials requirement and disclosing that the endpoint host is forwarded to Smithery's public search, which is a privacy behavior the parameter itself cannot express.

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?

"Review MCP Registry and Smithery listings" plus "Returns official MCP Registry and bounded Smithery listings versus live tools, transport and repositories" gives a specific verb-and-resource with the comparison target named. It is clear what comes back (directory data compared against a live probe), but it never contrasts itself with the many near-neighbours in the sibling list (check_mcp_server, preflight_mcp_listing, x402_listing_audit), so differentiation is left to inference.

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?

Usage is implied by the phrasing (compare listings to a live server) and there are useful scoping constraints such as "port 443, no credentials" and "query URLs skip it". However there is no explicit when-to-use statement, no when-not, and no pointer to check_mcp_server or preflight_mcp_listing as the lighter alternative for a plain liveness check.

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