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

No annotations are provided, so the description must carry the safety profile; it does signal a read-only public operation and discloses that results are annotated with epistemic status/freshness and that the default limit is 50 (max 200). It does not describe how multiple filters combine, what happens with offset pagination, or the response shape unless groupByCategory is set.

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 and numbered, which helps scanning, but the header '[STANDARDIZED SEARCH PROTOCOL - PUBLIC READ]' and internal references like '(Item 3)' and '(Item 11)' are noise the agent cannot act on. The core content is compact but not every sentence earns its place.

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 15 optional, heavily overlapping filters, no annotations, and no output schema, the description should explain how the filter axes relate and what the response looks like. It only addresses output shape for the groupByCategory case and leaves the interaction of tag/tags/category/mode/bucket/polarity/grain entirely unresolved.

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 15 parameters are already documented in the schema and the baseline of 3 applies. The description reinforces query/tag/tags/category/limit/groupByCategory but adds no combination semantics (AND vs OR across mode, bucket, grain, polarity, domain) beyond what the schema states.

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+resource (search knowledge items, rule cells, facts, invariants) with the distinctive twist that results carry epistemic status and temporal freshness. An agent can tell it apart from get_knowledge_item (single fetch) and get_knowledge_graph, though the phrase 'zero absolute truth assumption' is jargon that costs a little precision.

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 RULES block gives concrete operating guidance: supply 1-3 noun keywords in "query" or filter directly via tag/tags/category, and set groupByCategory=true for a breakdown. It stops short of naming alternatives (e.g., when to use hvs_query_segregated_memory or get_knowledge_item instead), so there is no explicit exclusion set.

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