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

Annotations already declare destructiveHint=true, idempotentHint=false, readOnlyHint=false, so the safety profile is known; the description still adds real value with "permanently," "cannot be undone," and the recovery path. It stops short of batch semantics — with up to 200 contacts per call, whether one bad entry aborts the whole request or partially applies is not stated.

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 compact sentences, front-loaded with a "WRITE:" marker that signals the mutation class before any detail. The endpoint is appended last where it belongs; nothing is wasted.

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 destructive, single-parameter mutation with no output schema and full annotation coverage, this covers intent, identity, irreversibility, and recovery. The remaining gap is error/partial-failure behavior on a 1–200 item batch, which an agent calling it would want to know.

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% and the item-level fields (name, email) are already documented in the schema, including the combined-identity note. The description's restatement of "identified by its email AND name" reinforces rather than adds to the schema, so the baseline 3 applies.

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 opens with a specific verb and resource ("permanently remove contacts from the account's contact list") and pins down the exact identity rule (email AND name). It is instantly distinguishable from sibling oksign_list_contacts (read) and oksign_upsert_contacts (add/update).

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 gives clear context for when this tool applies and names the recovery alternative ("re-add with oksign_upsert_contacts"). It does not explicitly say when not to use it (e.g., to prune a single contact after listing) or point at oksign_list_contacts for discovery, so it falls short of full routing guidance.

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