Generate a read-only payload for one item with task state and a board move patch (claim, progress, finish) to stage changes without writing.
Return the Proposal payload for one item — with task_state, a prepared board move (claim, progress, finish) as a patch; performs no write.
| Name | Required | Description | Default |
|---|---|---|---|
| at | No | ||
| slug | Yes | ||
| agent | No | ||
| task_state | No |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description asserts 'performs no write', but the annotation declares readOnlyHint=false, i.e. the tool is not read-only and may affect state. This is a direct conflict about the tool's safety profile, and an agent relying on the description could wrongly treat it as a harmless read. The partial disclosure that it returns a patch rather than applying it does not resolve the conflict.
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?
A single sentence that front-loads the return action and wastes no words. The em-dash construction is slightly tangled, but the size is well matched to the payload.
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?
There is no output schema and 0% parameter documentation, so the description carries the full burden, which is only partly met. It sketches the returned payload but does not explain what 'at' or 'agent' do, nor what a caller gains from receiving a patch they must apply themselves.
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% for all four parameters, so the description must compensate and does not. It names only task_state and gestures at possible move values (claim, progress, finish), leaving at, agent, and how 'one item' is identified (slug) completely unexplained.
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?
'Return the Proposal payload for one item' gives a verb and resource, and the second clause hints at the content (task_state, a prepared board move). However, 'Proposal payload' is undefined domain jargon, and nothing distinguishes this from siblings like read, compose, or search, which could plausibly return similar data.
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?
No when-to-use guidance, prerequisites, or named alternatives are given. The phrase 'performs no write' faintly implies a preview/dry-run role, but the agent is never told when to call propose instead of read, compose, or ask.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.