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

With no annotations, the description carries the full behavioral burden and does so well: it discloses a 256 KB size envelope, the retention policy (last 20 per run, kept 30 days), plan-gated behavior (Free watch-only saves nothing and returns would_save with exactly what would have been stored), and a security constraint (no passwords or API keys). That is unusually rich operational context.

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?

Four sentences, front-loaded with the action and timing, and each sentence carries distinct, necessary information: payload/size, retention, free-tier return semantics, security warning. No filler or restatement of the name.

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 mutation tool with no annotations and no output schema, the description covers what is stored, for how long, plan-dependent behavior, and the free-tier return field. Only minor gaps remain, such as error behavior and the explicit relationship to memory_resume for the recovery path.

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 already 100%, so the baseline is 3, but the description adds meaning beyond the field docs by enumerating what state should hold (cursor, ids done, partial results) and imposing a 256 KB limit on it. The 'ids done' phrasing also links to the otherwise-undocumented-in-description 'done' parameter.

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 ('save_checkpoint', 'Call after each completed step with the state you would need to continue') and makes the scope concrete with examples (cursor, ids done, partial results). It is clearly distinguishable from siblings like memory_resume and memory_list_checkpoints without opening any schema.

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?

Gives explicit timing ('after each completed step') and what the payload should contain, which is real when-to-use guidance. It does not name an alternative tool or a when-not condition (e.g., relative to memory_resume), so it falls short of the top band.

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