Update the persistent QA test suite

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

Annotations already flag destructiveHint=true and non-idempotent, and the description makes that concrete: matched cases are overwritten and mergeMode governs whether generated fields replace curated ones — the exact data-loss risk. It adds real context beyond the annotations, but the three mergeMode behaviors themselves remain unstated.

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?

Two dense sentences, front-loaded with the action and immediately followed by the matching/merge semantics. No filler, no restatement of the title.

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 6-parameter mutation the description covers the critical matching and overwrite behavior, which is the most important part. But with no output schema and a required `source` parameter left undefined, an agent cannot tell what the inputs mean or what a successful call yields.

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 17%, so the description must compensate. It does explain mergeMode's role and the normalization/matching key for cases, but the required `source` enum (report, exploration, feature, ticket, manual, generate, suite), plus sessionId, sourceUri and projectRoot, get no explanation at all — a significant gap for a required selector parameter.

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 concrete verb pair and resource: 'Add or update cases in the repo test suite', plus the matching key (feature + objective + steps) and the TC-id behavior. An agent can distinguish this from a read/export/lint sibling, though it never names an alternative explicitly to contrast with the generate path.

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?

Usage is only implied by the verb 'add or update' — there is no statement of when to prefer this over qa_suite_generate or qa_suite_read, nor of prerequisites (must a suite already exist? must projectRoot be set?). It hints at mergeMode as the decision point but gives no guidance on choosing a mode.

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