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

Annotations already cover safety (readOnlyHint, idempotentHint, destructiveHint), so the bar for adding value is high. The description clears it: it discloses parallel execution of the three endpoints, a 10-minute cache affecting freshness, and a specific error-handling behavior (explicit diagnostic for compra-format IDs instead of the old silent 'cabecalho: null'). None of this is visible in the 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?

Four short paragraphs in logical order: purpose, composition logic, ID provenance + cache, and edge-case handling. Every sentence carries distinct information — there is no filler, and the most decision-relevant constraint (conditional composition) is front-loaded next to the purpose statement.

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 an aggregator tool with 4 parameters, conditional behavior, composite keys, and an existing output schema, the description covers everything needed to invoke it correctly: which endpoints feed it, which params drive which behavior, where the inputs come from, cache freshness, and the malformed-input diagnostic. Return format needs no explanation because an output schema exists.

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, but the description adds genuine cross-parameter meaning: it explains the composite key numeroAta + unidadeGerenciadora used by the three secondary endpoints, maps API response fields (numeroControlePncpAta, numeroAta, unidadeGerenciadora, numeroItem) to the parameters, and clarifies the conditional role of numero_item. It also disambiguates the ata vs. compra formats of numero_controle_pncp_ata beyond the schema example.

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 'Dossiê completo de uma ARP em uma chamada', a specific resource (complete ARP dossier) and implied verb (compose/assemble in one call). It then details the composition (cabeçalho, saldo, adesões, unidades participantes), which clearly differentiates it from sibling tools like compras_arp_consultar, compras_arp_saldo_item, compras_arp_adesoes_item, and compras_arp_unidades_item that each cover one piece.

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 gives clear workflow guidance: the 3 IDs come naturally from compras_arp_listar or compras_arp_itens_listar, and numero_item controls whether only the header or the full dossier is fetched ('Se omitido, apenas o cabeçalho é consultado'). It also warns about the compra-format input pitfall. However, it never explicitly says 'use this instead of calling the four endpoints separately' or names when a sibling is preferable, leaving that exclusion implicit.

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