memory_review

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

With no annotations, the description carries the full burden. It states 'Read-only' and 'This tool never changes memory state,' which is the key behavioral trait. It also mentions the availability of view=help for further fields, but does not disclose other potential behaviors like output formats or error conditions.

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 concise, front-loaded with the purpose, and effectively structured. It uses a clear list for view options and a separate sentence for the non-mutation guarantee, with no wasted words.

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?

Given the output schema exists, return values need no explanation. The description covers purpose, usage contexts, view options, and the non-mutating behavior. The only gap is the 'data' parameter, but the help view and optional nature mitigate this. Overall, it is complete enough for a read-only inspection tool.

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 description adds substantial meaning to the 'view' parameter by enumerating valid values (overview/doctor/conflicts/conflict_detail/judgments/history/expired/audit/entities/help), which the schema lacks. The 'data' parameter remains unexplained, but the instruction to 'call view=help' when unsure about fields provides a path to discover it.

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 'Read-only Memory Arbiter inspection' with a specific verb and resource. It distinguishes from siblings by explicitly noting 'This tool never changes memory state', positioning it as the non-mutating inspection tool among memory_govern and memory_repair.

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 provides explicit when-to-use guidance: 'Use it when the user asks to inspect health, conflicts, conflict details, judgment history, memory history, expired memories, audit summaries, or entity coverage.' It does not name alternative tools explicitly, but the read-only emphasis implies when not to use it (for mutations).

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