handoff

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

With no annotations, the description carries the full load and it does disclose several non-obvious behaviors: session_id auto-resolution (latest active session or a new one), that next steps/open questions become 'leftovers', that to_agent posts a task to an inbox, and that Commons verifies the commit on GitHub. Gaps remain around authentication (api_key) and error/failure behavior, but the side-effect disclosure is unusually substantive.

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?

Dense but front-loaded: the core purpose leads, followed by conditional details in a logical order, with no filler sentences. Some internal jargon (resume(), leftovers) assumes ecosystem familiarity but is not padding.

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 15-parameter tool with 0% schema coverage, no annotations, and no output schema, the description is reasonably complete on fields and side effects. It still leaves auth expectations, which fields are actually needed (0 required is ambiguous), and the response shape unaddressed, so an agent must guess on some points.

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 description coverage is 0%, so the description must compensate and it does explain most parameters: summary, state, decisions, next_steps, open_questions, relevant_ids, repo (owner/name format), branch, commit, session_id, project, and to_agent. It leaves `goal`, `agent`, and especially `api_key` unexplained, so it partially but not fully covers the 15 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?

States a specific verb and resource ('Write a structured handoff packet') and enumerates its contents, making its function unmistakable. It also names the counterpart tool (resume()) that consumes the output, so an agent can place it in the workflow without opening a schema.

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?

Provides some conditional guidance ('Code work: pass repo...', session_id optional resolution, to_agent posting a task), which implies when the tool applies. However, it never states explicitly when to choose handoff over overlapping siblings like finish_work, record_decision, add_leftover, or submit_task, leaving the routing decision to inference.

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