Descartar itens do inbox

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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the agent knows it is a mutation that is supposedly non-destructive; the description could have clarified what "discard" actually means (remove from inbox, archive, or hard delete) and whether it is reversible. It adds only the confirm requirement and says nothing about partial failure when some ids are invalid or already discarded, which matters given idempotentHint=false.

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, no filler, with the action front-loaded and the precondition second. The length itself is fine; the problem is what is omitted, not what is padded.

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?

This is a mutation tool with two parameters, no output schema, and zero schema description coverage, yet the description covers only one of the two parameters and never indicates what the call returns or which ids failed. That leaves the agent without enough to invoke it safely on a batch of up to 100 items.

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%, so the description must carry parameter meaning, but it only clarifies `confirm` (must be true) and says nothing about `ids` beyond "um ou mais itens" — no note on the uuid requirement, the 1-100 range, or duplicate handling. It also conflicts with the schema, which lists only `ids` as required while the text says confirm is mandatory.

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?

"Descarta um ou mais itens da caixa de entrada" gives a specific verb (discard) and resource (inbox items) plus cardinality, so an agent knows this is a bulk mutation on inbox entries. It does not distinguish itself from nearby siblings such as list_inbox_items or confirm_inbox_item, so it stops short of a 5.

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 states a precondition ("Exige confirm: true") but never says when to choose discard over confirm_inbox_item or other inbox actions, nor when not to use it. There is no mention that discarding may be irreversible or how it interacts with inbox rules.

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