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

Annotations already declare readOnlyHint=true, idempotentHint=true, openWorldHint=true, and destructiveHint=false, so the safety profile is fully covered. The description adds useful non-annotation context: a cost of $0.02/call and a detailed preview of the returned reasoning (why each asset got its direction/confidence, the exposure-graph path, source links, corroborating sources). It does not mention auth or rate limits beyond cost, but the added transparency is meaningful.

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 front-loaded with purpose and output details, then usage guidance, then cost and a sourcing constraint. It is efficient overall, but the two sentences 'Takes the event id from those tools' and 'Use only with an event_id returned by events_since or impact_for' are partially redundant, slightly hurting conciseness.

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 simple read-only tool with one required string parameter, no output schema, and annotations that fully cover safety semantics, the description is complete: it says what the tool returns, when to use it, how it relates to sibling tools, the required input source, and the cost. Nothing an agent needs in order to invoke it 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?

Schema description coverage is 0% for the single event_id parameter, so the description must carry the burden. It specifies where the event_id must come from ('returned by events_since or impact_for') and uses it to scope the tool to exactly one event. This adds essential semantic meaning beyond the bare string type in the schema, though it does not describe the id format itself.

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 verb ('Plain-language explanation') and resource ('ONE event's impacts'), and details exactly what the explanation contains (direction/confidence reasoning, exposure-graph path, source document link, corroborating sources). It also distinguishes this from sibling tools impact_for and events_since by framing itself as the 'reasoning' layer rather than the raw impact data.

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?

It gives explicit when-to-use criteria: 'when an impact from events_since/impact_for is surprising and you need the reasoning before acting, or to log a rationale.' It also states a hard prerequisite and restriction: 'Use only with an event_id returned by events_since or impact_for.' No ambiguity remains about the appropriate context or the required input source.

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