web_lookup

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

With no annotations, the description must carry behavioral weight; it usefully discloses that the work is delegated to an external CLI agent with web access, implying nondeterminism and network dependency. It says nothing about latency, cost, failure modes, or whether the agent can execute code rather than just read, which matters for a delegated-agent call.

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?

Two dense sentences: the first establishes the mechanism and scope, the second front-loads the selection condition with an explicit "USE THIS". No filler or repetition.

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 four-parameter, single-required-field tool with a fully described schema, the description covers what the tool does and when to reach for it. The only gap is the shape of the response (free-text answer vs. structured citations), which is unstated and there is no output schema to cover 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 100%, so every parameter (query, cwd, model, effort) is already documented in the schema. The description adds no interpretation of these fields, so the baseline of 3 applies.

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 action (delegate a web/documentation lookup) and the concrete mechanism (Antigravity CLI / Gemini with web access), plus example use cases like library docs, API references, and current versions. It stops short of explicitly distinguishing itself from siblings such as deep_search or delegate, so an agent must infer which lookup path applies.

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 THIS when you need information you don't have or that may be newer than your training data" gives a clear trigger condition tied to knowledge gaps or recency. There is no statement of when *not* to use it and no named alternative among the sibling tools, so routing against deep_search remains ambiguous.

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