get_memory

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

With no annotations, the description carries the full burden. It discloses that the tool returns both memory files, a learned flag, and reflection state, and explains the conditional fallback behavior. It stops short of explicitly stating side-effect status or auth requirements, but 'Read' and 'Returns' make the read-only nature reasonably clear.

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 sentences, all information-dense and front-loaded. The first sentence states the core purpose, the second summarizes the return payload, and the third gives fallback guidance. No wasted words.

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?

Given the zero-parameter surface and an output schema that can define the return shape, the description provides complete operational context: what it reads, who should use it, what it returns, and what to do when the learned state is absent.

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?

There are zero parameters and the schema is empty, so there is no parameter-level meaning to convey. The description compensates by explaining what the tool reads and returns, which is the relevant semantic content for an argument-less call.

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 opens with a specific verb and resource: 'Read the distilled outreach memory', naming the style guide and strategy playbook. It clearly differentiates this tool by stating that drafting skills should use it instead of re-deriving style from raw history, which separates it from list_outreach and other siblings.

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 explicitly tells the intended callers (draft-outreach and draft-post skills) to use this tool for distilled memory, and provides a concrete fallback path (list_outreach or Notion log) and an actionable suggestion (run insaight-reflect) when memory has not been learned yet.

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