Attribution Coverage

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

Annotations already indicate a safe, idempotent read operation. The description adds behavioral nuance by distinguishing 'last real assessment' from 'last nightly intake,' and revealing it exposes research backlog/contradictions. This goes beyond basic read-only semantics.

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 a single dense sentence covering many output components. It is compact but somewhat run-on; it could be front-loaded and broken into clearer phrases. Still, no waste words.

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?

The description covers the key data dimensions (breakdowns, backlog, contradictions, top actors, research clock) and annotations/output schema handle safety and return format. Missing is any explanation of the optional actor parameter or the 'recent' list it scopes, which is a gap relative to the schema.

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 fully documents the one optional parameter (actor) with a clear description, so baseline is 3. However, the tool description never mentions the 'recent' list that the parameter refers to, creating a slight disconnect between the description's corpus-level scope and the parameter's scoping behavior.

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 clearly defines the tool as providing corpus-level attribution coverage metrics, distinguishing between genuinely assessed, actor-labelled, and uncovered threats. This differentiates it from sibling tools like get_attribution_evidence, which focuses on evidence for a specific entity.

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 implies use for understanding overall attribution quality but does not state when to use it versus alternative tools or explicitly mention the optional actor filter. No exclusion criteria or alternative tool names are provided.

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