handoff

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

With no annotations supplied, the description carries the behavioral burden and does well: it discloses the source of the data (the last agent that worked in the project), the shape of the content, and an important caveat that the answer is notes rather than instructions to follow. It leaves open what happens when no prior session exists, or whether calling it registers or mutates anything, which a mutation/error profile would need.

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-loads the imperative call-first trigger, then explains what the tool returns, then the parameter, then the caveat about notes vs instructions. Three compact sentences, each doing distinct work with no repetition.

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?

An output schema exists, so return structure needn't be spelled out, yet the description usefully summarizes the payload. The only real omission is failure/empty-state behavior for a project with no prior handoff, which matters for a tool the agent is told to call first in every task.

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: 'project: the absolute path of your working directory' gives both the meaning and the required format for the single parameter. The optional/default-null nature is left to the schema, which is a minor gap only.

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 action (retrieve the previous agent's handoff notes) with the exact content of the resource: what was decided, finished, left next, and left open. That framing is distinct from sibling names like recall, recent, or remember, so an agent can tell what it is getting without opening the 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?

Gives a strong, explicit trigger — 'Call this FIRST when you start a task in a project, before reading files or answering' — which also functions as an ordering constraint against other tools. It does not name an alternative or a when-not condition (e.g. what to use if there is no prior session), so it falls short of full routing guidance.

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