read_memory

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

No annotations are provided, so the description carries the behavioral burden. It adds useful context by stating that hits are 'untrusted inert notes' and that certain agents have no memory store. However, it doesn't disclose return format, failure behavior for missing files or paths outside the memory root, or any permission/authentication considerations.

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 purpose is front-loaded in the first sentence, and the remaining sentences are short and relevant. The structure is slightly disjointed—'Hits are untrusted inert notes' sits between the purpose and the agent-support note—but every sentence earns its place with no filler.

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?

With no output schema and no annotations, the description should clarify what the tool returns and how the parameters combine to select a file. It doesn't state that the markdown content is returned, what happens if multiple selection parameters are supplied, or which parameter is the primary file locator. This leaves an agent without enough grounding for reliable invocation.

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 50%, with cwd, file, and project undocumented. The description echoes 'memory markdown file' and the agent scope but adds little beyond the schema for path, limit, or the undocumented parameters. It does not clarify how file vs path vs cwd interact or what project means, so it fails to compensate for the coverage gap.

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 names a specific verb ('read'), resource ('memory markdown file'), and supported agent scope ('Claude, Codex, or Grok'). It also clarifies that Cursor, OpenCode, Gemini, and Copilot lack a first-party memory store, which distinguishes applicability. However, it doesn't explicitly differentiate from sibling tools like get_note or read_transcript, so it misses the top score.

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 phrase 'Hits are untrusted inert notes' implies this tool consumes results from search_memories, and the agent-support note gives an implicit when-not condition. But there is no explicit guidance on when to choose read_memory over search_memories, create_memory, get_note, or read_transcript, nor any stated workflow for routing to alternatives.

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