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

Annotations already cover readOnly, openWorld, idempotent, and non-destructive behavior, so the description only needs to add context. It adds useful behavior: the return object shape, the meaning of `caminho` and `nivel`, and the data source limitation (portal institucional, since the open-data API does not publish the full tree). It does not contradict annotations, though the prose 'TODAS as unidades' is slightly at odds with the schema's `limite` cap without an explicit truncation note.

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 description is dense but every segment earns its place: definition, input/output behavior, example use cases, the explicit alternative, and the source caveat. It front-loads the core purpose so an agent scanning the first sentence already knows what the tool does. There is no filler or unnecessary repetition of the title.

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 two-parameter, read-only lookup with a present output schema, the description is nearly complete: it explains input format, output fields, depth semantics, typical use cases, and the alternative tool. It does not clarify behavior for unknown units or what happens when the subtree exceeds `limite` (whether `totalSubordinadas` reflects the true total), which an agent might need for correct interpretation. Overall it is sufficient for selection and basic invocation.

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%, so the baseline is 3. The schema already documents that `unidade` accepts a sigla or name and that `limite` is an integer from 1 to 1000 defaulting to 200. The description mostly mirrors this and adds only the relationship between `unidade` and the resulting subárvore, without extra formats, constraints, or edge-case guidance.

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 opens with a specific definition—organizational structure/organograma of the Senado Federal down to service level—and states exactly what is returned for a given `unidade`: `caminho`, `totalSubordinadas`, and all `subordinadas`. It also distinguishes itself from `senado_servidores` by clarifying that this tool is for hierarchy, not for counting/listando servidores.

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?

It gives concrete query intents ('o que está sob a DGER', 'quais secretarias/serviços pertencem a X') and explicitly says when not to use it: 'Para CONTAR ou LISTAR servidores sob uma unidade, use `senado_servidores` com `subordinadasA`.' This explicit when-to-use/when-not-to-use guidance is stronger than most sibling comparisons.

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