111 Observe · Sense Reality

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

Annotations already cover safety (readOnly, idempotent, openWorld). Description adds behavioral detail: returns evidence, sources, uncertainty; authority level L0 OBSERVE; mentions epistemic tags. No contradictions.

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?

Description is very concise with no wasted words. It front-loads the purpose and lists modes. However, the jargon 'KERNEL 111', 'L0 OBSERVE' may be opaque without additional context, slightly reducing accessibility.

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?

Given 9 un-documented parameters and many modes, the description is far from complete. It mentions return types but fails to explain parameter roles or mode differences. Output schema exists but is not shown; description does not compensate for missing parameter semantics.

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% – the description does not explain any of the 9 parameters beyond listing some modes. It omits meanings for url, query, layers, actor_id, session_id, etc. This is a critical gap.

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 states the tool gathers evidence from reality, with specific verb 'sense' and resource 'reality'. It distinguishes from siblings arif_think (pure reasoning) and arif_route (domain compute), making purpose unambiguous.

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?

Explicitly states when to use: for evidence gathering with modes like search, fetch, etc. Directly advises against use for pure reasoning ('skip when pure reasoning → arif_think') and domain compute ('arif_route to GEOX/WEALTH/WELL').

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