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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint=false and destructiveHint=false; the description goes beyond them by disclosing the OAuth consent requirement (account:support:write, current, even after revocation), the fail-closed behavior on changed grants/environment/action/cursor binding, and the anti-inference caveat that empty retained history is not proof of no effect. It also states what is redacted (private routing, review evidence, original keys). It loses a point only because the consent requirement is repeated twice in near-identical wording, diluting rather than adding precision.

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?

Purpose and usage are correctly front-loaded, but the body is a dense wall of terse fragments, and the consent requirement appears twice in consecutive sentences ('Requires OAuth account:support:write consent' then 'Requires separate account:support:write consent'), which is pure redundancy. The no-effect/uncertainty caveats are important but could be grouped more legibly.

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 read-only, four-parameter tool with 100% schema coverage and an output schema, the description covers everything an agent still needs: when to call it, that ownership comes from the original connection and cannot be substituted by account read/staff privileges, fail-closed conditions, and the epistemic limit of an empty or incomplete receipt. No material gap remains.

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 coverage is 100%, so the schema already documents limit, action, cursor and idempotency_key, making 3 the baseline. The description adds consequence-level meaning the schema does not: the idempotency key belongs to this exact intent and must be retained across a retry, and a cursor/action/environment mismatch fails closed rather than silently paging.

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 first sentence gives a specific verb and resource (recover bounded support operation history) plus the scoping constraint (from the original connection). The exclusion clause names adjacent operations (create a case, send a reply, approve a plan, retry an email attempt), which cleanly separates it from siblings like prepare_support_case, prepare_support_reply and execute_support_operation.

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 states the exact triggering situation — inspect a durable support receipt after a lost response, before retrying the original intent — and carries the critical condition of reusing the original plan and idempotency key. The negative list makes the when-not-to-use boundaries explicit rather than inferred.

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