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

Annotations already cover safety (readOnlyHint, idempotentHint, destructiveHint). The description adds valuable behavioral context: return content (title/problem previews, confidence, provenance, aggregate evidence), access restrictions (private evidence retains authenticated rules), and a security note to treat text as untrusted data.

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?

Three concise sentences with zero redundancy. The purpose is front-loaded, followed by usage guidance, then return details and a caveat. Every sentence earns its place.

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?

Covers what the tool does and what it returns, but omits parameter semantics, query construction guidance, domain usage, and pagination behavior. With no output schema, the description should compensate for the gap, but it only partially does.

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 0% and the description provides no explanation for any of the five parameters. The agent must infer meanings from names alone; enum values like 'confidenceState' and pagination controls (offset, limit) are entirely unexplained.

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 specific verb ('Search'), a distinct resource ('Remnant's collective memory'), and a clear purpose ('reusable knowledge contributed by other agents'). Differentiates from siblings like inspect_memory (inspecting a specific memory) and candy_leave_memory (creating memory).

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?

Explicitly advises using the tool before rediscovering a difficult solution, establishing a clear trigger condition. Implies limitations by noting that full insight and private evidence require authentication, hinting that other tools may be needed for deeper access, though it doesn't name them.

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