checkpoint

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

With no annotations, the description carries the full burden and delivers the two most important write semantics: "Overwrites what it states, merges files," which tells the agent exactly what is replaced versus appended. It does not cover error behavior, size/rate limits, or whether the checkpoint requires an open investigation, so a few behavioral 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?

Front-loaded with the write-mode and purpose, then the field enumeration, then the call-timing directive. Every clause adds usable information given zero schema coverage, and there is 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?

An output schema exists, so return-value explanation is rightly omitted, and the description covers purpose, timing, and field intent for a seven-parameter write tool. Missing pieces are secondary: precondition (does an investigation need to be open?) and failure/overwrite-conflict behavior.

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 0%, so the description must compensate, and it largely does: it explains that decisions are "each with a one-line reason," that blockers are optional, and that in_progress should carry the investigation id. It still leaves the expected format of files entries and done granularity implicit across seven 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?

The description opens with an explicit mode marker ("WRITE") and a specific verb+resource: saving the session's working state so it survives context compaction. Enumerating the captured state (goal, done, in_progress, next, decisions, files, blockers) makes it clearly distinguishable from read-oriented siblings like session_state and memory_status.

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 concrete triggers: "Call after every completed subtask and before any long operation," plus a field-level convention to reference the open investigation id in in_progress. It stops short of naming alternatives explicitly (e.g., "read with session_state") or stating when not to checkpoint, so it is strong but not complete routing guidance.

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