Build connection graph

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

Annotations only declare readOnlyHint, openWorldHint, and destructiveHint. The description adds substantial behavioral context beyond that: the graph is built from a bounded slice of sessions, not all, and the bound is not a parameter. It gives a concrete measured example (6M sessions produced 10 nodes/8 links) and warns that nothing in the response marks the shortfall. It also documents that expression names are rejected with HTTP 403/500. This goes far beyond the annotations without contradicting them.

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 longer than average, but every paragraph earns its place: purpose, field-naming rule, alternatives, return type, and a safety caveat about bounded slices. It is front-loaded with the main action and then details. Slightly dense, but not wasteful; a 4 is appropriate given the complexity it must convey.

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 read-only graph tool with an output schema, the description covers all essential context: what the tool returns, how to select fields correctly, what to avoid, and a significant hidden limitation (bounded slice) with a measured example. It also names sibling tools for alternative result shapes. This is exceptionally complete given the tool's complexity and schema/annotation richness.

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 coverage is 100%, but the description adds critical meaning: it explains the src/dst fields take Arkime *db* names or dotted storage paths, and explicitly rejects expression names like ip.src/port.dst. It provides measured equivalences (srcIp/dstIp vs source.ip/destination.ip) and explains the effect of choosing dstPort. This is valuable semantic guidance beyond the schema's field descriptions.

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+resource: 'Build a source/destination connection graph of who talked to whom. Returns nodes and links between two fields.' It also distinguishes from siblings by naming arkime_multiunique and arkime_spigraphhierarchy as alternatives for different output shapes. This is clearly differentiated and purposeful.

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 use cases are given: 'useful for tracing lateral movement or mapping which hosts a suspect IP communicated with.' It directly names when-not-to-use: 'For distinct field-tuple pairs as text rather than a graph use arkime_multiunique; for a nested top-N hierarchy use arkime_spigraphhierarchy.' The description also warns about the bounded slice caveat, guiding the user to narrow with expression and time window.

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