Self-improving memory (report / optimize / record / state)

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

With no annotations provided, the description carries the full burden. It does disclose that the tool can both read (inspect, report, state) and mutate (steer, optimize, record) memory, which is useful. But it does not explain side effects of optimize, whether record permanently changes calibration, or what operational guarantees apply.

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?

A single, well-structured sentence front-loads the action and resource, then lists the key capabilities in a compact list. There is no filler or redundancy.

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?

The tool has five parameters, no required parameters, no output schema, and no annotations, which makes it moderately complex. The description does not clarify which parameters are required for op=record, what each op returns, or whether optimize has side effects. An agent could call it with invalid or incomplete parameter combinations and get no guidance from the description.

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 description coverage is 100%, so the schema already explains each parameter. The description adds high-level context around the op enum (report/optimize/record/state) but does not add meaning beyond what the schema provides.

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 names a specific resource ('arena-style skill memory') and a pair of clear verbs ('inspect and steer'), then enumerates the concrete capabilities: calibration buckets, verified win rate, threshold auto-tuning, and manual outcome recording. This clearly distinguishes jev_memory from the evaluate/decide/plan siblings by tying it to memory-specific operations.

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 implies usage: an agent would call this tool when it needs to inspect or modify skill memory. However, it gives no explicit guidance about when to prefer this over sibling tools, no exclusions, and no mention of which memory-related operations belong elsewhere.

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