gemini_code_search

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

With no annotations, the description carries full behavioral burden. It discloses synchronous execution and that an answer is returned, which is useful context. But it omits important operational details such as file-size limits, model cost, error behavior, and what exactly the answer contains.

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 efficient sentences with no wasted words. The opening 'Use a large-context model...' is slightly indirect, but the core action and synchronous behavior are front-loaded enough for quick comprehension.

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 covers the basic purpose and synchronous nature but leaves gaps regarding limits, cost, error handling, and return format. It is minimally adequate but not complete enough to fully guide correct invocation.

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 documents both parameters thoroughly. The description adds no syntax, format, or constraint details beyond what the schema provides, making the baseline 3 appropriate.

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: scans multiple repository files and answers architectural or code questions. The phrase 'Runs synchronously' implicitly distinguishes it from the asynchronous agent-job siblings (like dispatch_gemini_agent and check_agent_job), but it does not name any sibling explicitly, keeping it from a 5.

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?

Implies usage context (architectural or code questions across files) and notes synchronous execution, which hints at when to prefer it over async agent dispatch. However, it offers no explicit when-to-use/when-not guidance or named alternatives, leaving the agent to infer.

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