Save facts, decisions, or configuration under a key to checkpoint shared agent context; overwriting preserves the previous value in history for recovery.
Save a fact, decision or config under a key. This is the checkpoint. Overwriting keeps the old value in history.
| Name | Required | Description | Default |
|---|---|---|---|
| key | Yes | Unique key for this context entry | |
| tags | No | Tags for categorization | |
| value | Yes | The value/content to store |
Changes observed during successful MCP inspections.
v3.1.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond readOnlyHint=false, the description discloses real mutation behavior: keyed upsert semantics and the fact that overwriting preserves the old value in history, which tells an agent that a write is recoverable and non-destructive. It stops short of saying whether tags are replaced on overwrite or whether the previous value is returned, which matter for a checkpoint tool.
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 short sentences, front-loaded with the action and immediately followed by the behavioral caveat about overwriting. "This is the checkpoint" is slightly oblique but frames the tool's role economically; nothing else is wasted.
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 three-parameter, fully documented write tool with no output schema, the definition covers purpose, mutation safety, and history retention adequately. Minor gaps remain around what the call returns and how tags behave on overwrite, but nothing prevents correct invocation.
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% (key, value, tags all documented with types and limits), so the baseline is 3. The description adds only the idea that values are facts, decisions, or config, and that the key address is unique and overwritable; it adds no tag semantics or format guidance beyond 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?
States a specific verb (save) and resource (a fact, decision or config under a key), so the write-and-key semantics are clear. It does not, however, distinguish itself from the specialized siblings save_summary, save_failure, and record_success, which also write content, so an agent must infer which store to use.
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?
"This is the checkpoint" suggests a role, but there is no explicit when-to-use clause, no exclusion, and no named alternative among the many writing siblings. The usage is implied rather than stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.