Save structured task checkpoints with summary, decisions, and next steps so agents can resume project work later. Uses concise, model-readable facts instead of conversation logs.
Store a structured task checkpoint for later continuation. Use concise model-readable facts, not conversation prose.
| Name | Required | Description | Default |
|---|---|---|---|
| summary | Yes | ||
| evidence | No | ||
| decisions | No | ||
| next_steps | No | ||
| session_id | Yes | ||
| constraints | No | ||
| project_root | Yes |
Changes observed during successful MCP inspections.
v0.3.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations indicate a write operation (readOnlyHint=false), and the description confirms this with 'Store'. It adds the advice to use 'concise model-readable facts, not conversation prose', which is useful content guidance. However, it does not disclose persistence behavior, whether it overwrites existing checkpoints, or any side effects on other memory tools. No contradiction with annotations.
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?
The description is two sentences, front-loaded with the core purpose and followed by a concise content guideline. No wasted words, though the second sentence could be integrated more structurally.
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?
Given 7 parameters (3 required), no output schema, and minimal behavioral context, the description is inadequate. It lacks parameter semantics, usage guidance, and any explanation of how the checkpoint integrates with the broader memory system. An agent would struggle to call this correctly without external knowledge.
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%. The description mentions 'structured task checkpoint' but does not explain any of the 7 parameters (summary, evidence, decisions, next_steps, session_id, constraints, project_root). The required fields are entirely undocumented, forcing the agent to guess their semantics from names alone.
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 clearly states the verb 'store' and the resource 'structured task checkpoint' with a purpose ('for later continuation'). It distinguishes the concept from siblings like memory_remember by implying a checkpoint is a snapshot of progress, but it does not explicitly name alternatives or differentiate beyond that.
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?
No guidance is provided on when to use this tool versus alternatives like memory_remember or memory_recall. The description implies a use case (continuation) but gives no exclusions or explicit conditions. An agent must infer when a checkpoint is appropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.