desempenho

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

With no annotations the description carries the full burden and does well: it discloses that everything is computed server-side, that the price series is adjusted for corporate events with total return (dividends/JCP reinvested at data-ex) when there are proventos, that there are no costs and that 'premissas' ship in the response, plus a past-not-recommendation disclaimer. It omits operational traits like rate limits, caching, or error behavior, keeping it short of a 5.

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?

A single dense paragraph, front-loaded with the core 'what it returns' before methodology and parameter notes. Every clause adds information, though the density of domain terms (proventos, JCP, data-ex) makes it slightly heavy.

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?

Given no annotations, no output schema and 5 params at 0% coverage, the description supplies metrics returned, parameter formats, methodology assumptions and disclaimers, which is comprehensive. Minor gaps remain around empty-default behavior and response field specifics beyond retorno_total_pct.

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 0%, so the description must compensate and largely does: it specifies de/ate use AAAA-MM-DD and that media_curta/media_longa change the moving averages, while stating the defaults (21x100 and last-5-years). It does not explain what an empty de/ate (default "") or a 0 media value resolves to, which is the remaining gap for a zero-coverage schema.

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: it computes past performance metrics (return, max drawdown with peak/trough dates, volatility, moving-average crossover) for a single stock, buy-and-hold vs the crossover. The explicit focus on 'uma AÇÃO' distinguishes it from the sibling desempenho_fii and desempenho_etf, so an agent can route correctly without opening the 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?

Gives usable context ('ABERTO para qualquer ticker, sem chave', 'Medida do passado, não recomendação'), so the agent knows it needs no auth and returns a historical measure. But it never names when to prefer this over desempenho_fii/desempenho_etf or states any exclusions, leaving the routing condition (asset class) implicit.

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