Прочитати пам'ять

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

With no annotations, the description carries the behavioral disclosure burden. It does reveal that the facts persist across sessions and are automatically included in the system prompt each run万里. It does not, however, explicitly state that the tool returns these stored facts or that it has no side effects.

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 a single compact sentence with no filler. Each clause contributes useful information: what the facts are, that they persist, and that they are already available in the system prompt.

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 zero-parameter, read-only tool with no output schema, the description provides sufficient context: the nature of the memory, its persistence, and its automatic availability in the system prompt. A minor gap is that it does not explicitly describe the return value as the set of stored facts.

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 tool has zero parameters and an empty input schema, so there is nothing for the description to explain about parameters. The baseline of 4 applies because no parameter documentation is needed.

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 tool name and title provide the verb ('read') and resource ('memory'), and the description defines the content as 'project facts that survived the session'. It is clear enough, though the description itself does not explicitly state the retrieval action.

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 useful operational context: the facts are automatically injected into the system prompt on every run, so the agent should not redundantly add them to prompts. However, it does not specify when to call memory_read versus memory_add, memory_forget, or other siblings.

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