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

Goes well beyond the annotations by disclosing concrete operational limits: 10-second deadline, 256 KiB per response, at most 3 pages, 10 attempts/IP/24h shared with two named siblings. It also clarifies that saving stores a redacted snapshot for seven days and returns a private management key, and that saving never publishes — exactly the mutation-related context readOnlyHint=false leaves ambiguous.

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 what the tool does, then limitations, then the fingerprint workflow, then report handling — a sensible progression with no filler sentences. It is dense and telegraphic across many short lines, which is efficient for scanning but slightly reduces readability versus flowing prose.

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 return structure need not be described, yet the description still summarizes the key fields (protocol version, phase latency, tool count as complete or lower bound, connection_assessment). Combined with quota, retention, publishing path and explicit non-guarantees (no operator identity, permissions or answer quality), nothing an agent needs to call this correctly 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?

With 0% schema description coverage, the description carries the full burden and does so: url constraints are spelled out (public anonymous endpoint, ports 80/443, no credentials, query strings, fragments or redirects), save_report's side effects and return (private management key, seven-day retention) are stated, and expected_schema_fingerprint's semantics plus the warning that incomplete catalogs never prove a match are covered.

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 precise verb and resource — check a public anonymous Streamable HTTP MCP endpoint — and enumerates the exact protocol phases performed (initialize, initialized, tools/list). It also names the sibling it shares quota with (diagnose_http, assert_healthy) and the publishing sibling (publish_mcp_report), so an agent can distinguish it from those without opening any 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?

Explicit boundaries: point-in-time only, not scheduled monitoring; no tool invocation, OAuth or legacy HTTP+SSE; ports 80/443 only. It also prescribes the drift-detection workflow (save schema_fingerprint from a complete baseline, pass expected_schema_fingerprint later) and routes publishing to publish_mcp_report with confirm=true. It stops short of an explicit 'use diagnose_http instead when X' statement, leaving sibling selection partly inferred from the shared-quota mention.

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