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

With no annotations, the description carries the load, and it does disclose the returned fields (step, size, time) and that results are scoped to "your key". It does not explain what "recent" means (count/limit), ordering, or read-only guarantees, so meaningful gaps remain.

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?

One economical sentence with the resource and scope front-loaded and the returned fields in a compact parenthetical. No wasted text; could only be marginally tightened.

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 simple read tool with one optional param, complete schema coverage and no output schema, the description covers purpose, scope, and return fields adequately. Only the ambiguity of "recent" (limit/ordering) is left open.

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 100% and the single param is well-documented there, but the description still adds meaning: omitting run_id returns checkpoints across all runs, a conditional behavior not stated in the schema. That elevates it above the baseline 3.

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 ("List recent checkpoints") and clarifies scope ("for one run or all runs on your key"), which cleanly separates it from memory_save_checkpoint and memory_resume. It doesn't name siblings explicitly, but an agent can tell it is the read/inspection counterpart to the save tool.

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 "for one run or all runs" implies when the run_id matters versus when it can be omitted, which is useful guidance. However, it gives no explicit when-to-use versus alternatives like memory_resume, and no exclusions or prerequisites.

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