search

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

Annotations already establish read-only, open-world, idempotent behavior, so safety is covered. The description adds a genuinely useful behavioral fact the annotations cannot convey: 'No chat model is called', clarifying this is raw retrieval rather than an LLM-synthesized answer.

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 the verb and resource, then usage, then the disambiguating constraint. Nothing is redundant and every sentence carries 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?

With an output schema present and rich annotations, the description need not explain return values or safety. It covers purpose, usage trigger, and the chat-model caveat, leaving only the fetch-vs-search routing implicit.

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 query operator syntax, count bounds, localization, need_content, and ori_question are all fully documented in the schema. The description adds no parameter-level meaning beyond it, which is the baseline 3 case.

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 the web') plus the output shape (ranked results, source URLs, summaries). It clearly contrasts with the sibling 'fetch', which retrieves a known URL, though it never names the sibling or that distinction explicitly.

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?

'Use for current information' implies the trigger condition but does not state when not to use it or route the agent to the sibling 'fetch'. The usage context is present but thin for a tool that overlaps with a retrieval counterpart.

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