Retry a failed post. Publishes a failed post again, up to the retry cap. Send {} as the body.
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"id": "<id>"
},
"name": "retry_post"
}
}| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Numeric id. |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare destructiveHint=true, idempotentHint=false and openWorldHint=true, so the safety profile is carried by structured data. The description adds the genuine extra fact that retries are bounded by a cap, but does not disclose what happens at the cap (error vs. silent no-op) or what a retry does to the post's timestamps/engagement state.
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 short, front-loaded sentences do their job efficiently, but the third sentence ("Send {} as the body") is not merely filler — it is misleading given the required id. Every sentence should earn its place, and this one costs the definition accuracy.
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 one-parameter mutation with rich annotations and no output schema, little prose is needed, and the cap disclosure is a useful addition. However, the missing explanation of cap-exhaustion behavior and the contradictory body instruction leave an agent unsure how to invoke it correctly.
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% and the schema requires a single integer "id", yet the description instructs "Send {} as the body" — a direct conflict with the required parameter that would lead an agent to call the tool with no id. Rather than adding meaning to the parameter, the description actively undermines the schema.
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?
"Retry a failed post" gives a specific verb plus resource and narrows scope to posts in a failed state, which separates it from publish_post and schedule_post without naming them. It stops short of an explicit sibling comparison but the resource and precondition are unambiguous.
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 condition for use is implied by "a failed post" — you would not call it on a healthy post — but no alternative is named (e.g. use publish_post for a fresh publish, or what to do once the cap is hit). The retry cap is mentioned without saying what produces it or what happens when it is exhausted.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.