analyze_files

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

With no annotations, the description carries the full burden, and it discloses the most consequential trait: the files never enter the caller's context, only the answer does, which implies cost and context implications. It omits prerequisites (CLI availability/auth), latency expectations, and what happens on failure.

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 tight sentences, front-loaded with the action, then the trigger conditions, then the payoff. Nothing redundant and no repetition of schema content.

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 purpose, triggers and the key result-shape property ('only the answer does'). Remaining gaps are modest: model/effort selection guidance and error behavior, but an agent could call it competently as written.

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 coverage is 100%, so files, cwd, question, model and effort are already documented in structured form; the description adds no syntax or selection guidance for them. Baseline 3 applies. It also doesn't hint that model IDs come from list_models, a sibling that exists precisely for that.

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 first sentence names a specific action and mechanism: delegate file analysis to the Antigravity CLI (Gemini), plus the explicit contrast with 'reading files yourself'. It is clear what the tool does, but it never distinguishes itself from the 'delegate' sibling, which plausibly overlaps in purpose.

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?

Gives hard, checkable thresholds ('>200 lines' or 'more than 3 files') plus a task taxonomy (logs, database dumps, generated code, cross-file reviews, comparisons). An agent can decide on invocation without inferring anything.

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