remember

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

With no annotations, the description takes on the burden of behavioral disclosure. It explains that only drops are stored, that anchoring ties the verdict to a specific line, and that the memory entry dies when that line changes. It also clarifies grade semantics, adding value beyond the schema.

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 front-loaded with the core action and then explains grades and anchoring. It is concise, with each sentence contributing meaningful guidance—no fluff. It could be slightly tighter but is well-organized and readable.

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 write operation with 7 parameters and no output schema, the description covers the essential behavioral context: what is stored, when to use anchors, and the side effect of anchor invalidation. It does not describe the return value, which is acceptable for a write operation without an output schema.

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 high (86%), so the baseline is 3. The description adds semantic detail to the anchor parameters (pin to source line, memory dies on change) and clarifies grade meanings, going beyond the schema's lean field descriptions. This enriches the agent's understanding of parameter usage.

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: persisting graded verdicts to a review memory file. It specifies the verb (persist), the resource (.leveret/memory.jsonl), and the effect (prevents re-surfacing ungraded findings). It also distinguishes from siblings by noting only drops are stored and actionable findings are reported, not remembered.

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 provides usage context such as when to use anchors (instance verdict) vs omit (class-wide verdict) and explains that only drops are stored, implying when not to use it for actionable findings. It does not explicitly name alternative tools (like 'memory'), but the context makes the appropriate scenario clear.

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