checkpoint

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

Discloses that data is stored as type='checkpoint', fields are free-length, and checkpoints are meant for bearing. However, it does not specify whether writing a checkpoint overwrites or creates a new entry, nor the role of optional parameters like domain and session. With no annotations, this is a minor gap.

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 concise sentences that front-load purpose, then provide usage guidelines and storage semantics. No redundant information; every sentence adds value.

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?

Covers main aspects: purpose, usage guidelines, parameter roles, and storage type. Missing details on optional parameters and persistence behavior (overwrite vs append) but adequate for a tool with no annotations or output schema. References to pulse() and note() provide useful context.

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 description lists the four required parameters and notes they are free-length and should be readable summaries. However, it does not explain the optional domain and session parameters, and schema description coverage is 0%. It partially compensates but leaves ambiguity about the optional fields.

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 tool's purpose as snapshotting current working state with specific fields (intent/established/pursuing/open_questions). It distinguishes itself from sibling tools like note() by emphasizing that checkpoints are for bearing, not archives, and references pulse() for reading.

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?

Explicitly advises when to use (summary for next session) and when not to (timeless detail into note()). It also explains the consumption mechanism via pulse(). This differentiates from siblings effectively.

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