handoff_save

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

With no annotations, the description carries the behavioral burden. It discloses the destination (.handoff/), the preference for auto=true, and a security constraint. However, it does not explain whether the save overwrites existing files, what happens with the 'auto' flag, or if any special permissions are needed. Some useful context is provided, but significant behavioral details are missing.

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 concise sentences. The first sentence states the primary purpose, and the second packs in actionable guidance. No filler or repetition; every word earns its place.

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?

This tool has 16 parameters, no annotations, no output schema, and very low schema description coverage. The description only scratches the surface by mentioning goal, next_actions, auto, and security. It does not explain the full handoff pack structure, the meaning of the many array fields, the behavior of allow_secrets, or what the tool returns. For such a complex tool, the description is inadequate for reliable agent use.

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 input schema has 16 parameters but only 6% have descriptions (only next_actions has a schema description). The description adds semantics for goal and next_actions, and implies something about auto and secrets, but it does not clarify many parameters like done, doing, blocked, command, decision, question, memory_delta, file, link, root, and allow_secrets. Given the low coverage, the description does not compensate enough for the many undocumented parameters.

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 'Save a long-task handoff pack into .handoff/' with a specific verb and resource. It is easily distinguished from sibling tools like handoff_init, handoff_recall, and handoff_status, which have different actions (initialize, recall, status).

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?

The description gives practical usage guidance: 'Prefer auto=true' and 'Provide goal and up to 3 next_actions when possible.' It also includes a security rule: 'Never include API keys or tokens.' However, it does not explicitly mention when to use this tool versus alternatives, but the context of saving a long-task handoff pack implies when it should be used.

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