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

Annotations already declare read-only, idempotent, and open-world; the description adds substantial behavior beyond them: internal pagination up to max_paginas_varridas, client-side filtering, short-circuit at max_resultados, accent-normalized case-insensitive matching, and a 15-minute cache keyed by (palavra_chave + janela + caps). The bounded pagination honestly signals that the search is capped and not exhaustive, consistent with openWorldHint. No contradiction with annotations.

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?

Purpose is front-loaded in the first sentence, followed by mechanism, rationale, known limitation, and output shape in a clearly partitioned structure. The internal provenance note ('Achado da bateria A v0.3.5') adds no value for an agent, and the 169k/339-page anecdote, while illustrative of latency motivations, is slightly longer than strictly necessary.

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?

Complete for the tool's complexity level: it defines the output object inline, discloses the bounded-search behavior, the caching semantics, and the missing-UF limitation with a concrete remediation path. Nothing an agent needs to invoke it correctly or interpret results properly is absent.

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% with well-documented individual parameters, so the baseline is 3. The description adds meaning by explaining how the parameters interact — page scanning up to max_paginas_varridas, short-circuiting when max_resultados is reached, and the cache key spanning keyword+window+caps — which the schema does not convey. Not a 5 because the schema already carries most per-parameter semantics.

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+resource+scope: searches current ARPs whose `objeto` contains a keyword, with case-insensitive and accent-normalized matching. It references the exact upstream endpoint it builds upon and explicitly calls out the scenario it was created for (oportunidades_carona_arp), clearly distinguishing it from siblings like compras_arp_por_fim_vigencia and compras_arp_consultar.

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?

Explains why the tool exists — the upstream endpoint /modulo-arp/1.2_consultarARP_FimVigencia does not accept text filters — and when it applies (keyword search in `objeto`). It also gives an explicit when-not: for UF filtering it instructs crossing matches with compras_uasg_consultar via codigoUnidadeGerenciadora, naming the exact alternative and the reason.

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