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

Annotations already declare readOnlyHint=false, openWorldHint=true, and non-idempotent, and the description reinforces the write nature while adding value beyond them: the duplicate risk (no dedup enforcement is implied by the 'check first' advice), the minimal required field, and the underlying endpoint. It does not say what happens when a duplicate name is submitted (error vs. silent duplicate) or whether the created record is returned.

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 tight sentences with the operation class front-loaded ('WRITE:'), followed by scope, the key constraint, the pre-check, and the endpoint. Nothing is padded or repeated.

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 an 8-param create with nested objects and no output schema, the description covers the essentials an agent needs to invoke it: minimal required input and duplicate avoidance. The notable omission is the response shape — since there is no output schema, the agent cannot tell whether an ID for the new vendor comes back.

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 63% across 8 params, including nested 'address' and 'terms' objects that the schema already documents. The description adds only the required-field note, which duplicates the schema's 'required: [name]', and says nothing about the optional email/phone/terms/address semantics. Baseline 3 is appropriate since the schema does most of the work.

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 and resource ('creates a new vendor (supplier) record in SOS Inventory'), clarifies the domain synonym 'supplier', and is trivially distinguishable from siblings like sosinventory_create_customer or sosinventory_create_item. 'Only name is required' further pins down the minimal call shape.

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?

Explicitly routes the agent to sosinventory_list_vendors as a pre-check with the reason ('to avoid a duplicate'), which is the main usage decision for this tool. It stops short of stating when-not to use it (e.g. that an existing vendor should be updated instead), so it is clear but not fully exhaustive.

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