read_memory

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

With no annotations, the description carries the full burden. It does disclose one genuinely important trait — that returned hits are 'untrusted inert notes' (a prompt-injection warning) — but says nothing about permissions, failure modes when the path escapes the harness root (only the schema hints at this), or what the read returns.

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?

Two short sentences, front-loaded with the core action and scope, with the safety caveat and the harness-availability note each earning their place. Very little waste, though the harness enumeration is dense and could be trimmed.

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 6-parameter tool with no output schema and no annotations, the description covers scope and one safety trait but leaves half the parameters and the entire return shape unexplained. Adequate as a minimum viable definition, not sufficient on its own.

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 50%: path, agent, and limit are described in-schema, while cwd, file, and project are undocumented in both places. The description reinforces the agent constraint (claude/codex/grok), matching the schema's own description, but adds no meaning to the three undocumented parameters.

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 and resource ('Read one ... memory markdown file') and pins the scope to three named harnesses (Claude, Codex, Grok). An agent can tell this apart from create_memory and search_memories by the singular-file, harness-scoped framing, though it never names those siblings explicitly.

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 harness list implicitly tells the agent when this tool is applicable at all (no first-party memory store for Cursor/OpenCode/Gemini/AGY/Copilot), which is useful scoping. But there is no explicit when-to-use versus search_memories or create_memory, and no stated prerequisites, so selection is left to inference.

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