One-shot: test transform rules without registering them

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

No annotations are provided, so the description carries the burden. It does disclose several behavioral traits beyond the schema: it fetches a URL directly (side effect), applies patches non-persistently ('without registering them'), returns a sample with before/after values plus match count, and doesn't require the proxy running. However, it doesn't specify what happens on fetch failure, whether patches are applied in order, or whether the sample is a subset or all matches. Decent but not exhaustive.

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 sentences with zero waste. The front-loaded opening sentence contains the core purpose, the second sentence frames the use case and ties to the sibling tool, and the third sentence states the one operational caveat. Efficient and well-structured.

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 self-contained probe tool with 100% schema coverage and no output schema, the description covers the essential operational details: what it returns (modified samples + match count), when to use it (pre-update_transform validation), and a key runtime prerequisite (proxy not required). The only slight gap is describing failure behavior on network errors, but given the schema richness and clarity of purpose, the description is nearly complete.

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 both parameters (url, patches) already described in detail in the JSON schema, including the patch sub-object structure (path, set, where), wildcard syntax examples, and special token formats like __NOW__ and __NOW_PLUS_<N><UNIT>__. The description adds the conceptual role of these parameters as a validation pipeline but doesn't substantially extend the schema's parameter-level docs. Baseline 3 is appropriate given full schema coverage.

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 tool fetches a URL, applies given patches, returns a sample of modified fields (before/after) plus match count. It explicitly says this is a 'one-shot' test of transform rules without registering them, which clearly differentiates it from siblings like proxy_update_transform (which registers rules). The verb+resource+outcome are all specific.

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 explicitly states when to use this tool: 'Useful for verifying patch paths and wire values before calling proxy_update_transform.' This directly frames it as a pre-validation step before a sibling tool. It also discloses 'Does NOT require the proxy to be running,' which clarifies the operational precondition. This is explicit when/when-not guidance naming the alternative.

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