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

Annotations only say this is a non-read-only, non-destructive, closed-world write; the description adds the genuinely useful behavioral fact that the handoff persists at the top of every read until closed, which no annotation conveys. It also adds a hard authoring rule about essence that is not derivable from structured fields. It stops short of naming what is returned (the #handle needed for superseding or closing) or what permissions/state are required to close it.

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?

Two sentences, front-loaded with the call trigger, with no filler. The parenthetical about a 'frozen catalog without that field' is unexplained jargon that costs the reader a beat, which keeps it below a 5.

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 10-parameter mutation tool with no output schema, the description covers the essential decision (use this vs. arroway_log) and the persistence behavior of what it creates. It leaves two gaps an agent would care about: what the call returns (presumably a handle) and how the handoff is subsequently closed, plus the meaning of the 'frozen catalog' carve-out.

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 the baseline is 3; the description earns above that by adding meaning the schema does not carry, notably that essence is authoring-mandatory even though it is absent from the required list, with a narrow exemption for a frozen catalog. It does not clarify how supersedes, read_handles, or addressed_to interact in practice, so it is not exhaustive.

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 states a concrete effect: calling it 'leaves a HANDOFF served at the top of every read until someone closes it,' which tells an agent exactly what artifact is created and how it behaves. It also explicitly separates this tool from the sibling that handles the opposite case ('a completed task ends in arroway_log instead'), so the agent can choose between the two without opening either 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?

The trigger condition is stated precisely: 'Call when you STOP with the task unfinished.' The exclusion and alternative are also given in the same sentence, routing completed work to arroway_log. It also states the lifecycle exit condition (until someone closes it), which is the implicit alternative to using this tool at all.

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