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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so safety is covered. The description goes beyond that by spelling out the return payload shape ("numeros", "membros", "menu") and the null semantics ("numeros; null = todos"), which is genuinely additive; it stops short of mentioning permissions, volume or pagination.

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?

The purpose and scope come first, then the field enumeration, then the sibling boundary — good front-loading. It is dense with enumerations, but each clause maps to a distinct returned field, so little is wasted.

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 carries the burden of describing return values and does so thoroughly, including the auxiliary collections (numeros, membros, menu). The remaining gap is minor: target_user_id/admin behavior lives only in the schema, but that schema is fully annotated.

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?

There is a single optional parameter, target_user_id, and schema description coverage is 100% ("(Só o admin da plataforma) userId da conta a operar"). The description adds nothing about it, so the schema does all the work — a baseline 3 under the high-coverage rule.

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 os agentes da conta") and enumerates exactly what is returned: name, entry-agent flag, handover rules, instructions, KB tag with document counts, products, team, button text, numbers and entradaEm. It also explicitly draws the boundary with get_agent_config, so an agent can distinguish this from the main-agent config tool without opening a schema.

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 final sentence gives clear routing: this tool lists multiple agents, while get_agent_config still owns key, model, schedule and calendar. That is a usable when/when-not signal, though it never mentions the mutating siblings (create_agent_profile, update_agent_profile) that an agent might also consider.

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