agy_review

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

No annotations are provided, so the description carries the full behavioral burden, and it discloses almost none. It does not say whether the operation is read-only or whether it can modify the target directory, that the prompt is sent to an external Google Gemini model, anything about latency/cost, or what the result looks like. Only the enumerable evaluation dimensions (manutenibilidade, segurança, performance, bugs) add substance.

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?

One dense sentence with the action front-loaded and no filler; the four review dimensions are packed in efficiently. It is well-sized for a single-purpose tool, though packing purpose, mechanism and scope into one sentence makes it slightly harder to scan.

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 3-parameter tool with no output schema and no annotations, the definition is adequate on purpose but thin on everything an agent needs to invoke it confidently: expected output form, whether the directory is read or written, and where the review is executed. Nothing required is present in structured fields to compensate.

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%, with model, prompt and directory each documented in the schema itself, so the baseline is 3. The description adds nothing about prompt formatting, directory semantics, or model selection trade-offs beyond what the schema already states.

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 (revisão técnica aprofundada) and concrete resources (código, diffs, implementações), plus the delivery mechanism (Antigravity / agy CLI) and the evaluation axes. It is clearly distinguishable from agy_plan, agy_exec, agy_command and agy_validate_tests by the object and intent, though it never names a sibling to sharpen 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?

Usage is only implied: the agent can infer 'use this when you want a deep code review', but there is no explicit when-to-use vs when-not, no routing to agy_plan for planning or agy_validate_tests for test validation, and no prerequisites stated.

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