gemini_analyze

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

No annotations are provided, so the description carries the full disclosure burden, and it does supply the single most important trait: 'Read-only.' That is a genuine, useful behavioral commitment. However, it says nothing about the fact that this dispatches work to an external specialist model, the cost/latency implications, or caching behavior (params like tier/model/noCache hint at this but the description is silent).

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 terse fragments with no filler, and the usage trigger and safety note are packed into minimal space. The opening phrase is a noun clause rather than a front-loaded verb, which slightly weakens scannability, but overall it is efficiently sized.

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?

This is a complex 11-parameter tool with no output schema and no annotations, so the description must carry more weight than it does. It omits what the tool returns, that it delegates to an external LLM specialist (with cost implications), and how it relates to the sibling analysis/review tools, leaving meaningful gaps for an agent deciding whether and how to call 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% across 11 parameters, so the schema already explains diff, tier, model, paths, checks, workdir, objective, timeoutMs and constraints thoroughly (e.g. the tier enum guidance). The description adds no additional parameter meaning beyond what the schema provides, so the baseline of 3 is 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?

The fragment 'How a broad or unfamiliar part of the code fits together' implies a code-comprehension/analysis function, but it never uses a verb+resource construction to state what the tool actually does. It also offers no differentiation from the many sibling review/diagnose tools (gemini_review, codex_review, codex_diagnose, edge_cases), so an agent must infer the boundary from the name alone.

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 trigger 'Use before editing code you have not read' is a concrete, actionable condition that tells the agent when this tool applies. It stops short of naming alternatives or stating when-not-to-use (e.g. versus gemini_review), so it is clear context without exclusions.

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