Hand unfinished work to the next session — or take over what another session left

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

Annotations only cover openWorld/idempotent/destructive, so the description carries the lifecycle: write creates a 🤝 card the human can see and correct and that the next session picks up at brain_sync; take marks it claimed for peers; done archives the card; continues closes the earlier card as "continued by" this one. It also discloses the scope split between the machine-local automatic layer and the brain-travelling card, which is behavior an agent cannot infer from the schema.

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?

Front-loaded with the tool's identity and the write action, then walks take/done/list in order — every sentence carries routing or lifecycle information. It is dense and long, and the closing "Machine-local for the automatic layer; the card travels with the brain" is terse to the point of ambiguity, but nothing is 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 16-parameter, four-mode tool with no output schema and thin annotations, the description covers the action surface, triggers, and state transitions well. Minor gaps remain: it does not say how the agent reads the taken work after claiming it, or what happens on an unknown/stale id or session prefix.

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%, so baseline is 3; the description goes further by mapping parameters to actions ("Call {action:"write"} … with the task, what is done, what is NEXT in order, the files and how to verify"), which tells the agent which fields matter per mode. It adds little about id/canvas/project/continues beyond what the schema already states, so it stays below a full 5.

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 names the resource (session handoff card) and enumerates four concrete actions — write, take, done, list — each with its own trigger, so an agent can route without opening the schema. It also differentiates itself from siblings by tying the card to brain_sync and session start, which no sibling does.

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 when-to-use for every branch: write when context/usage limit is near, day ends, blocked, or switching tool; take before continuing someone else's work so peers see it is claimed; done on completion; list to see everything open. It also names what to do instead of the anti-pattern ("Never ask the human to paste a summary into the next session — write a handoff").

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