Discard QA session state

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

Annotations already declare destructive, idempotent, and non-read-only, but the description adds material context beyond them: deleted=true confirms absence even for unknown/expired IDs, irreversibility that survives restart, storage-failure behavior where memory stays intact, and the explicit note that host tasks and model executions are unaffected. These are exactly the operational details annotations cannot convey.

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?

Front-loaded imperative sentence, then a bulleted block where each line carries a distinct fact (mutation behavior, idempotency, irreversibility, failure recovery, unaffected systems). No sentence restates the name or the annotations verbatim, and there is no padding.

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?

With an output schema present, the description need not explain return fields, and it correctly stops there. For a single-parameter destructive mutation with full annotation coverage, everything an agent needs to call it safely and recover from edge cases is present.

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% and the schema itself documents the qar- pattern, so the baseline is 3. The description nonetheless adds dispatch-relevant meaning: run_id can select a session at any stage with no prior advance or finish, and it points at list_qa_orchestrations as the recovery path for an unknown ID.

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 ('Delete one QA session from memory and configured recovery storage') and immediately distinguishes itself from the sibling that shares its domain by naming finish_qa_orchestration as the retain-outcome alternative. An agent can differentiate it from advance/get/list/prepare with no schema inspection.

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 when to use this tool ('to retain a final QA outcome, use finish_qa_orchestration' implies deletion is for discarding), relaxes a constraint ('no prior advance or finish required'), and routes the agent to list_qa_orchestrations to recover a lost ID with instructions for disambiguating matches. Explicit alternatives and conditions are provided rather than implied.

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