kb_search

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

No annotations exist, so the description carries the full behavioral burden. It discloses search scope across three knowledge sources, and 'search' implies a read-only operation, but it says nothing about result ranking, deduplication, or how the two sources are merged.

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?

Three short sentences, front-loaded with what it searches, then when to use it, then scope — no repetition of the name or the schema. Every sentence adds a distinct piece of 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?

An output schema exists, so return-value documentation is unnecessary, and this is a simple two-parameter read tool. The remaining gap is query semantics, which is the one thing an agent genuinely needs before invoking it.

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% — neither 'query' nor 'limit' has any description, and the description never clarifies query syntax (keywords vs. natural language vs. path globs) or what 'limit' controls or defaults to. With low coverage the description is required to compensate, and it does not.

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?

It names a specific verb+resource ('search field notes from previous rebuild attempts') and enumerates the content types covered (routes, gotchas, versions) and the three source locations (repo KB, wheel seed notes, $UOS_HOME/knowledge). This clearly separates it from siblings like kb_index, kb_new, and kb_check, though it never explicitly names an alternative.

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?

'Search BEFORE starting — prior art saves the whole session' gives a concrete trigger condition, which is real usage guidance rather than filler. It stops short of an explicit when-not or a named alternative tool, so it sits at 'clear context, no exclusions.'

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