Graph Campaigns

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is covered. The description adds value beyond annotations by warning that a cluster of one event documented multiple times can look identical to a real multi-event campaign until the agent reads the duplicate_risk evidence fields (distinct_member_dates, date_span_days, shared_title_tokens). That is non-obvious behavioral context which prevents an agent from misinterpreting results.

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 core identity of the tool is front-loaded ('Campaign clusters the engine assembled from the similarity graph'), and the differentiation from sibling tools comes in a clearly marked second sentence. The first sentence is dense with enumerations, but each item corresponds directly to actual return fields, so there is no filler.

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 one documented parameter and an output schema, the description fully explains the resource's origin, content, cluster semantics, the duplicate_risk caveat, and the naming neighbor tools. No information needed to call it correctly or interpret its output 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 100% — the only parameter, limit, already carries a full schema description (default 15, max 50). The description adds nothing parameter-specific, but it does not need to; the schema fully documents the single input.

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 precise verb ('reports') and a well-scoped resource: campaign clusters the engine derived itself from the similarity graph (connected components + label propagation), with an explicit list of contents (label, cohesion, actors, techniques, IOCs, nation-states, per-member fields). It also differentiates itself from get_campaign_intelligence and list_campaigns, making the tool distinguishable from its closest siblings without opening any schema.

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 explicit routing rules: use get_campaign_intelligence when looking up a NAMED campaign from threat text, use list_campaigns for the roster of named campaigns, and use this tool for the clusters the engine derived itself. Each alternative is named with a criterion that selects it, leaving the agent with no inference to make.

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