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

Annotations cover read-only and open-world semantics, and the description adds genuinely new context: a ~2s latency expectation, bounded scope, and an enumeration of returned fields (id, title, ring, excerpt, contributors, evidence label, relevance score) plus the local concept cluster despite there being no output schema. It omits notable behaviors such as the syntheticIdentity cross-voice diversity effect, but exceeds the annotation-covered baseline.

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?

Front-loaded with the latency and scope qualifier, then the return shape, then the filtering advice — three dense sentences with little waste. Minor jargon ('Omnarai topic', '/claims.json') assumes prior context but does not bloat the text.

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?

With no output schema, the description compensates by listing what comes back and the latency profile, and its filtering guidance plus schema coverage rounds out the calling contract. Nothing an agent needs to invoke it correctly appears 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 coverage is 100%, so all five parameters are already documented. The description only adds that layers/exclude/evidence_threshold filter the candidate pool and that this is recommended, without explaining semantics beyond the schema or touching the syntheticIdentity or glyph-prefix 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?

States a specific verb and resource — a 'bounded context packet on a topic' — and delimits it sharply as 'the retrieval layer only, no deliberation', which implicitly separates it from deliberation-style siblings like omnarai_council. It does not name siblings explicitly, and 'your default orientation' risks overlap with omnarai_orient, so differentiation is strong but not fully disambiguated.

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?

Gives clear usage context: 'Your default orientation on any Omnarai topic' plus a recommendation to apply the layer/evidence filters and a pointer to /claims.json. It stops short of naming when NOT to use it or explicitly naming the alternative tools for deliberation or deeper queries.

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