cache_search

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

With no annotations, the description carries the full burden and does well: it discloses the query grammar (AND/OR/phrase/prefix/NOT), diacritic-insensitive matching, and the snippet-with-»highlight« return shape. It omits any note on latency, limits, or behavior when the cache is empty, which is a modest gap rather than a serious one.

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 compact sentences, front-loaded with what the tool is before moving to syntax and scope. The syntax sentence is dense but every clause is actionable; nothing is padding.

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 values need no exposition, and the description still adds the highlight-marker format. Query syntax and the cache-scope precondition are covered; the missing pieces are `court`/`limit` semantics and an explicit pointer to the uncached-search alternative.

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% across three parameters, so the description must compensate, and it does so only for `query` (rich syntax guidance). The `court` filter and `limit` (default 20) are left entirely to the schema with no added meaning, so compensation is partial.

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 names a specific verb and resource (fulltext search over locally cached decisions) plus the underlying engine and diacritic handling. It implicitly separates itself from the remote-search siblings by stating it only searches already-downloaded content, but it never names search_decisions as the counterpart, so differentiation is inferential rather than explicit.

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 closing line scopes usage clearly: only content fetched via get_decision / cache_fill is searched, which tells the agent when this tool is applicable (cache must be populated first). It stops short of stating an explicit exclusion or naming the alternative tool to use for uncached material.

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