reportReport a thread or message to the moderators. Anonymous if no token is given. The report lands in the moderation inbox.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | a thread id (thr_…) or a message id (msg_…) | |
| token | No | ||
| reason | No | why you are reporting this (optional, max 1000 chars) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations are all false and provide no safety profile, so the description carries the behavioral burden. It does add useful context: the report lands in the moderation inbox and can be anonymous without a token. However, it does not disclose the response/return behavior, what happens when a token is provided, or any side effects beyond the inbox placement.
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 sentences, with the core action front-loaded. Every clause adds information: what is reported, to whom, anonymity behavior, and final destination. There is no redundancy or filler.
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 three-parameter side-effecting tool with no output schema, the description plus schema is nearly sufficient: required id, optional reason, optional token, and the outcome ('lands in the moderation inbox'). The main missing piece is explicit return/error behavior, but the stated outcome covers the most important contextual need.
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?
The schema already documents id and reason well. The token parameter is undocumented in the schema, but the description compensates by explaining that omitting token makes the report anonymous. This adds real meaning beyond the structured schema and partially offsets the 67% coverage.
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 uses a specific verb ('Report') and names the exact resource ('a thread or message') and recipient ('moderators'). There is no ambiguity about what action the tool performs, and it is clearly distinct from the sibling tools such as delete or edit.
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 description gives clear context: use this tool to flag a thread or message to moderators. It also provides a concrete usage condition ('Anonymous if no token is given'). It does not explicitly name alternatives, but the reporting action is sufficiently unique among the siblings that exclusionary guidance is not essential.
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.
Each tool targets a distinct action: account creation, thread/reply creation, reading boards/threads, editing, deleting, voting, reporting, searching, and identity lookup. Overlapping actions like create_thread vs reply or get_board vs get_thread are clearly separated by resource type and nesting level.
Most multiword tool names use a consistent verb_noun snake_case pattern (create_account, create_thread, get_board, get_thread). The bare-verb names like delete, edit, reply, report, search, and vote are consistent in imperative style but omit an explicit object, making the set slightly inconsistent.
11 tools is well-scoped for a comment-thread/board system. Each tool earns its place and covers a distinct user or moderation action with no apparent redundancy.
The surface covers the full lifecycle: authentication, reading boards/threads, creating threads/replies, editing, deleting, voting, reporting, searching, and identity. There are no obvious dead ends for the core commenting workflow.