memory_checkpoint

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

The description reveals a key side effect: it saves both as a memory entry and a standalone file, going beyond the minimal annotation hints. It does not disclose potential overwrite behavior, storage costs, or how the checkpoint relates to other memory state. Annotations already indicate it's not read-only, so additional context earns credit but could be deeper.

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, under 20 words, and front-loads the core purpose. Every word contributes meaningful guidance, with no repetition of schema or annotations.

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?

Despite having an output schema, the input semantics are severely underspecified. The phrase 'Full state checkpoint' implies automatic capture, but the parameters require explicit supply of state fields. This mismatch could confuse an agent about what it must provide. The description lacks essential information about how to construct a valid checkpoint call.

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?

The schema lists five parameters (agent_name, summary, blockers, active_branch, remaining_tasks) with zero descriptions. The tool description does not mention any of these parameters or explain how to fill them. With 0% schema coverage, the description fails entirely to compensate for the missing parameter guidance.

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 identifies the tool as a 'Full state checkpoint' and states it saves to both memory and a standalone file. It distinguishes itself from memory_write by emphasizing full-state snapshots. However, it uses a noun phrase rather than a strong action verb, leaving the exact operation slightly implicit.

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?

'Do every 10-15 min or before risky ops' provides explicit, concrete timing and trigger conditions for use. It does not mention when *not* to use it or suggest alternatives, but the guidance is actionable and context-rich.

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