Checkpoint

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

Without annotations, the description fully bears the burden. It clearly states the tool is read-only ('does not write anything itself') and describes that it returns a procedure for the agent to execute, along with memory call and continuity info. This discloses the key behavioral trait of non-mutation.

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 moderately long but every sentence serves a purpose: stating the trigger, listing the returned procedure components, and explaining how to handle uncertain parameters. It front-loads the core purpose and usage, making it easy to scan. Slightly verbose but not wasteful.

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 no output schema, the description adequately explains what is returned (procedure steps, memory call, previous checkpoint). It covers all parameters with necessary context. While exact format details are omitted, the description provides enough for an agent to understand the tool's role and output.

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?

All four parameters have descriptions in the schema, but the description adds significant context: defaults for scope, detailed explanation of author vs 'anyone' with use-case rationale, instruction to ask user if project omitted, and timezone purpose. This goes beyond the schema's enums and short descriptions.

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 defines the tool as an end-of-session bookend paired with get_session_start, specifying its triggered by user phrases like 'checkpoint' and listing the exact steps it returns. This distinguishes it from sibling tools, particularly get_session_start, by its role as a session closer.

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?

Explicit guidance on when to call (user phrases) and what the agent must do after receiving the procedure (execute steps, ask for project tag if omitted). It also clarifies that the tool does not write anything itself, setting clear expectations for agent action. No direct alternative comparisons are needed given its unique purpose.

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