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

Annotations already declare readOnly/idempotent/non-destructive/openWorld=false, so the safety profile is covered. The description adds genuinely new behavioral context: results are cached and point-in-time, and calling it will NOT trigger a live scan — an important side-effect expectation. It omits pagination and result-shape details, but for a read tool that is minor.

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?

Two compact sentences, front-loaded with the free/read-only/cached framing before the scan-vs-cache distinction. Nothing is wasted, though it could have traded a few words for parameter guidance.

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 tool with ten optional filter parameters and no output schema, the description leaves the entire query surface undocumented and gives no hint about what the response contains. The safety/behavior side is adequate, but the invocation surface is not.

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?

Ten parameters with 0% schema description coverage, and the description says nothing about any of them — not sort, query, source, outcome, or any filter. An agent must infer the meaning of every filter from its name alone, so the description fails to compensate for the coverage gap.

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: inspecting ProofRail's latest scan of public MCP endpoints drawn from public registries. It distinguishes itself implicitly from siblings like mcp_radar_changes by being a point-in-time snapshot rather than a diff, but it never names an alternative explicitly.

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?

The 'cached, does not trigger a live scan' clause implies when this is appropriate (cheap/read-only inspection rather than a fresh scan), but there is no explicit when-to-use/when-not guidance and no sibling is named as the alternative.

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