search_knowledge

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

No annotations are provided, so the description carries the full burden, and it delivers: it discloses the read-only safety profile ('CONFIRMATION TIER: READ OPERATION... SAfe to call freely'), the automatic internal routing behavior, and the composite return nature ('combined results from both FTS keyword search and semantic retrieval'). It stops short of describing result ordering or deduplication across the two retrieval modes, which would complete the picture.

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?

Well-structured with labeled sections (AUTOMATIC TRIGGERS, CONFIRMATION TIER, PARAMETERS) and a front-loaded summary sentence. Minor redundancy: the dual-combination behavior is stated in the opening, the routing paragraph, and the closing return sentence. Every section otherwise 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?

For a simple two-parameter read tool, the description covers purpose, triggers, routing behavior, safety, parameter semantics, and query strategy. With no output schema present, the main gap is the structure of result items, but for a search tool this is a minor omission given everything else is covered.

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 coverege is 0%, so the description must compensate, and it does: it explains that query accepts 'keywords or natural language' (non-obvious and important for a hybrid-search tool) and that limit means 'Max results.' For a two-parameter tool this is adequate, though it could add detail on whether limit applies per source or in total.

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, and method: 'Search findings using both semantic similarity and keyword matching.' It explicitly differentiates from siblings by naming them: 'no need to choose between search_findings and retrieve_findings.' An agent can tell this tool apart from its siblings without opening any 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?

An 'AUTOMATIC TRIGGERS' section lists three concrete trigger conditions, including the tie-breaker 'Not sure whether to use keyword or semantic search.' It explicitly handles the when-not case by routing around search_findings and retrieve_findings, and adds query-strategy guidance distinguishing broad exploration from specific facts.

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