set_vendor

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

With no annotations, the description carries the full behavioral burden. It usefully discloses that this is preview-first and that apply remains unavailable until an adapter and canary are complete, which is important safety context. However, it omits permissions, reversibility, rate limits, and what a preview returns.

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 only two sentences, but it is under-specified rather than concise. For a 10-parameter tool with no annotation or output schema coverage, the brevity leaves critical information missing. The second sentence about apply being unavailable is front-loaded but the whole text does not earn its place as sufficient documentation.

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 a 10-parameter mutation tool with no annotations, no output schema, and 0% schema description coverage, the description is far too sparse. It does not explain parameters, return behavior, when to use the tool, or how preview and apply modes relate. It is inadequate for the complexity of the interface.

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?

The schema has 10 parameters with 0% description coverage, and the description mentions none of them. Parameters such as mode, dryRun, previewToken, idempotencyKey, and the expected hash fields are left completely undocumented. The description adds no semantic meaning beyond what the bare schema provides.

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 says this is a preview-first replacement for a deprecated immediate vendor write, which signals a vendor mutation tool. However, it never explicitly states what the tool currently does (e.g., previews vendor changes) and the note that apply remains unavailable leaves the actual operation ambiguous. It also does not differentiate from sibling upsert_vendor by name.

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 only usage context is that this replaces a deprecated immediate write and that apply is unavailable. There is no explicit guidance on when to choose this over upsert_vendor or get_vendor, nor any prerequisite or exclusion conditions. An agent must infer usage entirely.

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