Infrastructure Pivots

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

Beyond the annotations (readOnlyHint, idempotentHint, destructiveHint), it explains important behavioral details: results derive from the same indicator universe as the correlation graph, pivots carry value_threat_count thresholds, and confidence is rarity-based. It also clarifies a real semantic trap — that zero pivots can mean either a genuine negative or merely no pivotable indicators, and that labels are excluded by design so the returned evidence is not overstated.

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 front-loads the primary purpose and then earns every subsequent sentence with real-value guidance: value_threat_count interpretation, coverage semantics as denominator, and when to route to get_similar_threats. It is dense but appropriately so for a tool whose output requires careful interpretation.

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?

There is one required parameter, an output schema is present, and independent annotations already cover read-only/idempotent safety. The description supplies the missing interpretive context — how to read pivot_count/value_threat_count and why zero results can still be meaningful — making this complete for the agent to invoke and consume the tool responsibly.

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 schema already gives 100% coverage of the only parameter, threat_id, with a format example. The description adds no additional parameter detail beyond framing it as the 'given threat,' so the baseline of 3 applies; the schema is doing the heavy lifting here.

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 clear verb and resource: "surface cross-threat infrastructure links" for a given threat, listing the exact artifacts involved (IPs, domains, hashes, DNS overlaps). It differentiates itself from get_similar_threats by explicitly disclaiming TTP/actor-based similarity, leaving no ambiguity about scope.

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 says when to use it (to find shared infrastructure across threats) and when not to ('labels are deliberately not pivotable') with a direct pointer to the alternative: 'Use get_similar_threats for TTP/actor-based similarity instead.' It also tells the caller how to interpret edge cases like pivot_count=0 with scorable_iocs > 0 vs = 0.

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