web_search

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

With no annotations provided, the description carries the full burden and it delivers meaningful context: it discloses the underlying services (Tavily, Firecrawl), the default model (GLM-5.2 via Ark), and even the caching behavior via the 'cached' flag. This goes beyond a simple 'search tool' and gives the agent insight into how results are generated and possibly stale.

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?

The description is well-structured: a purpose sentence followed by a bulleted return list. The return list is necessary because no output schema exists, and each bullet earns its place. It is slightly more verbose than necessary but remains focused and front-loaded with the main function.

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?

The description covers the search pipeline, default model, return values, and caching, and it links to a sibling tool (get_sources) via session_id. With no output schema, this is essential. It does not provide explicit alternatives for search-related choices (gemini_search), but that gap is primarily for usage guidelines. Overall, the description is reasonably complete for a read-only search tool with a rich schema.

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 100%, so the schema already explains all three parameters clearly. The description adds little to parameter understanding, though it does connect the returned session_id to get_sources, which is output-related. Baseline 3 applies per the rubric.

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 clearly states the tool 'performs a deep web search' using Tavily + Firecrawl and synthesizes a cited answer with an LLM. This specific pipeline (multi-source + synthesis) distinguishes it from siblings like gemini_search, which likely uses a different search mechanism.

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 phrase 'deep web search' implies when to use it, and the return field 'pass to get_sources' suggests a workflow. However, it does not explicitly state when to use this tool versus alternatives like gemini_search, web_fetch, or web_map, nor does it mention any exclusions.

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