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

The description explicitly states that with peek=false the tool 'lê tudo inteiro e marca' — i.e., it mutates read-state — while the annotations declare readOnlyHint=true. This is a direct inconsistency: the tool is documented as capable of a write operation that the annotation denies. Per the rubric, a contradiction of the annotations scores 1.

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 compact sentences, front-loaded with the resource and its contents, then behavior, then usage. Every clause carries information, though the nested parenthetical about peek is a little dense.

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 no output schema, the description usefully enumerates the returned sections (pending items, requests, recent conversations) and adds a multi-chat safety constraint. It is nearly complete for a 2-param read tool, aside from not addressing the limit parameter or naming sibling alternatives for related reads.

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% (baseline 3), but the description goes beyond the schema by spelling out the non-default semantics of peek ('peek=false lê tudo inteiro e marca'), which the schema only implies via the default's wording. The limit parameter is left to the schema, keeping it just short of a 5.

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 ('Espia a caixa deste agent na AICQ') and even enumerates what is shown (pendentes with id/sender/first line/taker, pedidos, últimas conversas). It is clearly distinguishable from siblings like aicq_send or aicq_ask, though it never names an alternative tool explicitly.

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?

Gives explicit invocation conditions ('Rode só quando o dono pedir ou a tarefa da sessão envolver a AICQ') and a concurrency constraint ('com vários chats no mesmo handle, só um lê a caixa'). No sibling alternative is named for the case where the agent wants filtered search rather than a raw peek.

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