read_memory

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

Annotations already declare readOnlyHint=true, but the description adds a real behavioral constraint not present in structured fields: access is limited to a whitelist, so only certain names are valid. It does not describe what happens on a non-whitelisted name, but the whitelist disclosure is meaningful context beyond the annotation.

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 compact sentence with the read/list dichotomy front-loaded and the exclusivity rule trailing as a constraint. Nothing is wasted, though the extreme brevity leaves room for a few more useful facts at little cost.

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?

An output schema exists, so return values need not be explained, and the tool is low-complexity with two optional params. Still, the description never addresses error behavior for a non-whitelisted or missing name, which is the main failure mode an agent would hit.

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%, so the description carries the burden, and it does explain the role of each parameter (name = a memory file to read, list = enumerate whitelist entries) plus their exclusivity. However, it gives no value format for either — no example name, and no hint what the list string should contain — leaving the agent to guess.

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+resource (读取记忆文件) and covers both operating modes (read one file, or enumerate via list), which separates it from the write_memory sibling. It does not explicitly contrast itself with write_memory, so it falls just short of full sibling differentiation.

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 one concrete usage rule — name and list are mutually exclusive, choose exactly one — which is genuine routing guidance. It does not say when to use this tool versus write_memory or when a read would fail, so the guidance is implied rather than complete.

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