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

With no annotations, the description carries the full burden and delivers: a 256 KB size cap, Pro retention policy (last 20 per run, 30 days), and critically the free-tier behavior (no-op returning would_save). It also flags a security constraint (no passwords/API keys). This is unusually rich behavioral disclosure.

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 dense sentences, front-loaded with the trigger condition, then retention/limit facts, then the security warning. No filler and every clause carries operational information.

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?

Although there is no output schema, the description covers the return behavior for free tier (would_save payload), storage limits, retention, and the safety constraint. An agent has everything needed to call this correctly on both tiers.

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%, so the baseline is 3, but the description adds real meaning beyond the schema: the semantic content expected in 'state' (cursor, ids done, partial results) and a hard size limit of 256 KB JSON for that parameter. That constraint is not in the schema.

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 states a specific verb+resource (save a checkpoint of resumable state) and frames it around the trigger point ('call after each completed step'). It is easily distinguished from siblings like resume and list_checkpoints.

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?

It gives an explicit call condition ('after each completed step') and names what belongs in the state (cursor, ids done, partial results). It doesn't explicitly contrast with resume/list_checkpoints or say when not to call, so it stops short of a 5.

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