RecallNest

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

With no annotations provided, the description carries the full burden. It successfully discloses the ephemeral nature ('compact checkpoint', 'without polluting durable memory') and recovery intent ('next session to recover'). However, it lacks details on retention policy, whether repeated calls overwrite or append, and specific lifecycle behavior.

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?

Two sentences, zero waste. Front-loaded with the core action, followed immediately by the specific usage context. Every word serves either definition or differentiation.

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 10-parameter storage tool with 100% schema coverage and no output schema, the description is complete. It explains the conceptual model (checkpoint vs. durable memory) and recovery workflow, which is sufficient given the rich parameter documentation in the schema itself.

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%, establishing a baseline of 3. The description adds valuable semantic context by explicitly mapping the conceptual elements ('decisions, open loops, and next actions') to the workflow of resuming work across sessions, helping the agent understand why each parameter matters for the checkpoint pattern.

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 provides a specific verb ('Store') and resource ('compact checkpoint of the current work state'). It effectively distinguishes from siblings like store_memory or pin_memory by emphasizing the 'checkpoint' concept and explicitly mentioning it avoids 'polluting durable memory', clearly positioning it as ephemeral session state management.

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 states when to use ('when a task spans windows or terminals') and implicitly defines when not to use (for durable/long-term storage, use other memory tools instead). The 'without polluting durable memory' phrase provides clear guidance on tool selection against the 20+ sibling storage tools.

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