web_lookup

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

With no annotations, the description carries the full burden; it usefully discloses the backend (Antigravity CLI, Gemini with web access), which tells the agent this is an outbound delegated call. It says nothing about whether the operation is read-only, latency or cost characteristics, failure modes, or what the response looks like.

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 sentences, front-loaded with the mechanism and followed by the usage trigger. No wasted words and no redundancy with the schema.

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 tool with no annotations and no output schema, the description should indicate what comes back — raw page text, a synthesized answer, or citations — since the schema cannot. It also omits any note on result freshness or scope limits, leaving an agent unable to predict the return value's shape.

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 query, cwd, and model are already documented in the schema, including the advice to normally omit model. The description adds no guidance on how to phrase the query or when to supply cwd, so baseline 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?

States a specific verb and resource — delegate a web/documentation lookup to the Antigravity CLI — and enumerates the content types it handles (library docs, API references, error messages, current versions). It does not differentiate itself from plausible siblings like deep_search or delegate, so an agent still has to infer the boundary.

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 'USE THIS when you need information you don't have or that may be newer than your training data' clause gives a clear positive trigger. However, it names no alternatives and no exclusions, so the choice between web_lookup, deep_search, and delegate is left unstated.

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