session_ping

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

No annotations provided, so description carries full burden. It states the tool is 'extremely fast — one Redis SET, no blocking operations', which discloses performance characteristics. Does not mention overwriting behavior or data size limits, but overall transparent about its lightweight nature.

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 paragraphs: first explains usage and purpose, second adds technical details. Every sentence is meaningful, no repetition. Front-loaded with the key instruction 'call this every ~5 tool calls'.

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 checkpoint tool with 5 parameters and no output schema, the description covers behavior, usage frequency, rationale, and technical implementation. It is complete enough for an agent to understand when and how to invoke it correctly.

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% and each parameter has a description. The tool description adds context beyond the schema: it explains how parameters like 'files_touched' and 'next_step' are used to reconstruct state on the next provider. This adds value beyond the schema definitions.

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 it is a 'lightweight checkpoint' that stores current task and files touched. It distinguishes itself from siblings like session_start and session_end by focusing on periodic checkpoints during a session, solving provider-switching issues.

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 instructs to call 'every ~5 tool calls or whenever you complete a significant step'. Explains the context of provider switching and why this tool is needed (e.g., Claude context limit hit, window crash). Provides clear guidance on when to use.

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