jiji_prepare_action

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

Beyond the annotations (readOnlyHint=false, destructiveHint=false, openWorldHint=true, idempotentHint=false), the description adds genuinely non-obvious behavior: preparing itself performs no mutation, no MCP tool can approve the prepared action, and sensitive categories are owner handoffs. The one gap is that it doesn't explain that a pending action artifact is created and how it is later approved (presumably in the Jiji app), leaving some ambiguity about what "prepare" actually persists.

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 core promise (prepare, no mutation, owner review) before examples and exclusions. Dense but every clause carries information; five short sentences for a tool with 35 operations is reasonable. The middle example list is slightly noisy but serves as enum orientation.

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?

Given 35 operations, a free-form nested `parameters` object and 0% schema coverage, the description does the right thing by delegating schema discovery to jiji_capabilities and covering the safety model. Since an output schema exists, return values need not be explained. The only shortfall is not naming the status-checking sibling to close the prepare→approve→verify loop.

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% across three required parameters, so the description must compensate. It partially does — the example categories loosely group the 35-value `operation` enum and it routes the agent to jiji_capabilities for exact schemas — but it says nothing about `purpose` (a 5-500 char rationale string) or the free-form shape of the `parameters` object, so the caller still has to fetch schemas elsewhere.

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 specific verb+resource: "Prepare a mapped account/marketplace change for exact local owner review," and enumerates example categories (save/follow, notifications, business details, advert close/delete/publish, feedback, chat status) that map onto the operation enum. It distinguishes itself from approval/execution tools by stating "No MCP tool can approve it," though it never names the closest sibling (jiji_action_status) for follow-up.

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 clear conditions: use this to stage a change, and use jiji_capabilities to discover exact parameter schemas. It also states explicit exclusions — payments, passwords, identity and permanent account deletion are owner handoffs, not this tool's job. It stops short of stating what to call after preparing (status checking), which keeps it from a 5.

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