Conftest pull

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

Annotations already indicate destructiveness, idempotency, and open-world behavior. The description adds that the tool depends on an external binary and the policy directory must be within allowed paths. However, it doesn't clarify overwrite behavior, whether the directory is created, or the exact side effects beyond annotation hints.

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 extremely concise—two sentences covering the tool's purpose and usage context. Every sentence adds value without redundancy or fluff.

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 simplicity (2 params, no output schema, no nested objects), the description covers purpose, prerequisites, and a usage hint. It lacks information about return values or errors, but for a download tool returning nothing is often acceptable. Overall, it meets the needs for selection and 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?

Both parameters (`url` and `policy`) are fully described in the input schema (100% coverage). The description's phrase 'hydrate a local `policy/` directory' adds minimal extra meaning. According to rules, baseline 3 applies when schema coverage is high and description adds little new information.

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 clearly states the action ('Download Rego policies') and the source/destination ('from an OCI registry or Git repository into a local directory'). It also names the underlying command (`conftest pull`), making it highly specific and distinguishable from sibling tools like `conftest_test` or `conftest_push`.

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?

It explicitly states the use case ('hydrate a local `policy/` directory before running `conftest_test`') and lists prerequisites (conftest on PATH or CONFTEST_BINARY set, path constraints). While it does not explicitly mention when not to use it, the context is clear enough.

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