find_generated_artifacts

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

With no annotations provided, the description carries the full burden. It discloses that it scans build_output/outputs/build roots (read-only) and classifies findings. It does not mention auth needs, rate limits, or behavior when no artifacts are found, but the read-only nature and scanning scope are useful behavioral context beyond the schema.

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?

The description is three sentences, front-loaded with purpose and artifact types. Each sentence earns its place: the first states what it finds, the second explains the scan scope and read-only nature, and the third points to a complementary resource. No wasted words.

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?

Given the tool's complexity (4 optional parameters, output schema present), the description is nearly complete. It covers what it finds, where it scans, and how to interpret results via another resource. The main gap is explicit guidance on when to choose it over alternative search tools, but that is partially addressed by the purpose statement.

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 all four parameters are documented in the schema. The description adds marginal value by listing example artifact kinds that align with the 'kind' parameter and mentioning the build roots relevant to 'repo', but these are already present in the schema. Baseline 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 description uses a specific verb ('Locate') and resource ('generated-code artifacts'), enumerates the artifact types (pass dumps, .pto MLIR, kernel/orchestration C++, dfx outputs), and scopes the search to the workspace. This clearly distinguishes it from siblings like search_code or find_entrypoints, which target different resources.

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 description implies usage by stating it locates generated-code artifacts and suggests combining with the debug/codegen-inspection resource. However, it does not explicitly say when to use this tool versus alternatives (e.g., search_code, find_entrypoints) or when not to use it. This is minimum viable guidance.

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