memory_repair

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

With no annotations provided, the description carries the full burden of transparency. It discloses key behavioral aspects such as preferring dry_run, requiring authorized=true for cleanup/activation/metadata changes, and clarifying the maintenance vs. governance boundary. While it doesn't describe the effects of each individual task, it points to help for field-level details, which compensates. No contradictions with annotations (none exist).

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?

The description is well-structured and front-loaded: the first sentence states the core purpose, followed by a compact task list, then two sentences of operational guidance. Every sentence adds value, and there is no fluff or repetition. It is appropriately sized for a tool with many task variants.

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?

Despite the complexity of multiple task modes, the description is sufficiently complete. It lists all task options, explains when to use memory_govern instead, gives operational hints (dry-run, authorization), and directs to task=help for field details. An output schema exists, so return-value documentation is unnecessary. The description provides enough for an agent to correctly invoke the tool or seek further help.

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?

The input schema provides only generic 'task' and 'data' fields with no enums, giving 0% coverage. The description compensates by enumerating all valid task values (split/rebuild_claims/rebuild_embeddings/cleanup_history/cleanup_vectors/resync_vectors/set_entity/activate_pending/semantic_control/notice/help) and explains the behavior of task=help. It also mentions that authorized=true may be needed in data, adding meaning beyond the schema.

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 clearly states the tool's purpose: 'Memory Arbiter maintenance and repair.' It explicitly names the resource (Memory Arbiter) and provides a specific verb (maintenance and repair). It also differentiates from siblings by stating this is for maintenance, not fact governance, and points to memory_govern for that. This is specific and distinguishes the tool.

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?

The description gives explicit usage guidance: 'Prefer dry_run first where available' and identifies when authorization is needed. It also tells the agent when not to use this tool ('This is for maintenance, not fact governance; use memory_govern for user-authorized fact decisions') and recommends falling back to task=help if unsure. This provides clear context and alternatives.

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