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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered; the description adds real behavioral context beyond that: result ordering ('best and newest matches first'), the empty-query behavior, and the fact that long bodies are truncated in results. The truncation warning is exactly the kind of surprise-reducing detail annotations cannot express. It doesn't mention pagination or result cap behavior, which keeps it from a 5.

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?

Two sentences, zero filler, and the highest-value facts (what it searches, ordering, no-query fallback, truncation, sibling handoff) all appear before any lower-priority detail. Every clause carries distinct information.

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?

All five parameters are optional with full schema documentation, annotations cover the safety profile, and there is no output schema to explain. The description fills the remaining gaps an agent needs — when to call it, what ordering to expect, what happens with no query, and why to switch to get_knowledge — leaving nothing material unstated.

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 the baseline is 3, but the description adds meaning the schema cannot: omitting the query parameter is what triggers the recent-items listing mode. Query syntax (phrases, OR, -exclude) and the kind/mine/tags/limit filters are left entirely to the schema, which is appropriate given full coverage.

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 ('Search your workspace's shared knowledge') plus distinguishing behavior: relevance-then-recency ordering and the no-query fallback that lists recent items. It also names the sibling it complements (get_knowledge) so an agent can distinguish a search from a full-text read without opening either 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?

Gives a clear when-to-use directive ('Search before starting work') and an explicit routing condition to the alternative tool when bodies are truncated. It stops short of stating when NOT to use it (e.g., when the item id is already known and get_knowledge should be called directly), but the positive guidance and alternative are both concrete.

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