manage_handoffs

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

Beyond annotations, it discloses that the tool 'Adds or marks notes; never deletes', reinforcing the destructiveHint=false annotation, and it explains lifecycle behavior: the next start_here shows the note after hard rules, and picked-up notes stop showing. It also gives return shapes ('Returns the note or {notes}'), though it does not discuss permissions, limits, or idempotency explicitly.

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 short, front-loaded, and segmented by action. Every sentence contributes either identity, action semantics, exclusion, or return behavior, with no redundant filler.

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 an 8-parameter multi-action tool with no output schema, the description covers purpose, per-action behavior, exclusions, lifecycle interaction with start_here, and basic return shape. It does not mention project scoping or the optional limit/model/include_picked_up parameters, but those are fully documented in the schema, so the description is largely complete.

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 100%, so the schema already documents each parameter including action, project, handoff_id, where_i_was, next_step, limit, model, and include_picked_up. The description adds action-level semantics (what leave/pickup/list do) but does not add extra parameter details beyond that, making 3 the appropriate baseline.

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 opens with a concrete identity ('Notes from one AI to the next') and then defines each action (leave, pickup, list) in operational terms. It explicitly distinguishes itself from sibling concepts: 'Not a session summary and not a todo', which separates it from manage_todos and generic session tools.

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?

It gives explicit when-to-use guidance per action: 'leave: when you must stop mid-task', 'pickup: once you continue from a note', and 'list: open notes'. It also states exclusions ('Not a session summary and not a todo') and the relationship with the sibling start_here, leaving little inference required.

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