Caixa de entrada

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

Beyond readOnlyHint/openWorldHint, the description discloses three useful traits: the caller's own messages are excluded, results are grouped per conversation, and IDs are ready to hand to reply_message. The one significant omission is that markRead advances cursors and acks on Discord—a side effect hidden in one schema field on an otherwise readOnly-annotated tool—and the text/json output modes are also unmentioned.

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?

Three dense sentences, front-loaded with scope, then filtering caveat, then window semantics. Nothing repeatable or decorative; every clause carries information.

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?

With eight optional parameters, no output schema, and only two annotation hints, the description does solid work: it defines the item set, the exclusion rule, the grouping, and the window behavior. It falls short on the markRead mutation and the format switch, which materially affect what an agent gets back and what side effects it triggers.

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 100%, so all eight parameters are already documented, which sets the baseline at 3. The description reinforces the 'hours' fallback window and the implicit dms/mentions/watched filters, but adds no syntax or interaction detail the schema does not already contain.

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?

States a specific verb and resource ('Lista o que chegou e ainda nao foi tratado') and enumerates the four sources it aggregates: DMs, mentions, watched channels, and gateway events. That enumeration plus the 'grouped by conversation' output hint clearly separates it from siblings like read_messages or list_dms, which lack the unhandled-items framing.

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 'still unhandled' scoping tells the agent this is a triage-first tool rather than a raw history reader, and it names reply_message as the natural downstream step. It never explicitly says when to prefer read_messages or mark_read instead, so there is no exclusion guidance, but the usage context is unambiguous.

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