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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds genuinely useful behavior: the five-minute token lifetime, the confirmation requirement, and an explicit statement that nothing is applied. This is meaningful context beyond structured fields. It does not describe preview contents beyond 'exact', so not a 5.

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, front-loaded with purpose, then the confirmation requirement, then the return behavior. 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 annotations carry the safety profile and there is no output schema, the description adequately explains that it returns a preview plus a token. A bit more on what the preview contains or how the token is used would complete it, so a 4.

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?

With only one parameter and 0% schema description coverage, the description leaves the three sub-fields (provider, vendor_name, gl_account_id) essentially unexplained. It adds a hint that names/codes come authoritatively from the workspace's cached chart, which is useful, but field-level meaning is not conveyed.

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+resource ('Prepare creating/replacing a manual vendor rule') and immediately clarifies the preview-vs-apply distinction with 'it does not apply the change'. An agent can distinguish this from save_vendor_rule without opening the schema.

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?

Explains the two-step flow clearly ('Requires confirmation... returns an exact preview and a five-minute confirmation token'), which gives strong context for when to call it. However it never names the follow-up tool (save_vendor_rule) that consumes the token, nor does it contrast with preview_delete_vendor_rule.

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