path_diversity

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It reveals that data comes strictly from observed AS paths (no inference), that shares are per-upstream coverage and can sum past 1.0, that `is_tier1` marks Tier-1 core, that `diverse=false` indicates single-threaded or thinly observed behavior with a `reason` field, and that the view is control-plane rather than data-plane. It also states the default window and what widening it does.

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?

The description is dense but well-structured: a one-sentence lead, then layered detail on semantics, usage, and caveats. Backticks and line breaks make fields and concepts scannable. Some concepts like observed-vs-inferred and control-plane vs data-plane are repeated across paragraphs, but the length is largely justified by the tool's complexity.

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?

Despite no output schema, the description documents key return concepts (`share`, `total_vantage_points`, `is_tier1`, `diverse`, `reason`) and explains how to interpret them. It also covers the default time window, the optional `prefix` parameter, and the tool's limitations. It does not specify date string formats or include an example, but for a read-only analysis tool this is nearly complete.

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?

The input schema provides only names and types with no descriptions. The description adds meaningful context for `prefix` (a CIDR the ASN originates, useful for MOAS or specific route redundancy) and implies the role of `start`/`end` via the default 14-day window. However, it does not clarify the expected format for `start`/`end` or explicitly define `asn` beyond the general origin-network context, so compensation is only partial.

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 specific, concrete function: computing the observed propagation/path-diversity tree of an origin's announcements as they fan out through upstreams to collectors. It clearly identifies the resource (origin ASN, upstreams, collectors) and distinguishes itself from a data-plane traceroute, which helps separate it from sibling path-oriented tools.

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 description gives clear context for when to use the tool: to see which upstreams actually carry a network's routes and how lopsided that distribution is. It also explains when to pass the `prefix` parameter (for MOAS prefixes or checking a specific route's redundancy) and notes the default 14-day window. However, it does not explicitly compare against any sibling tools or state when not to use it beyond the traceroute caveat.

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