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

With no annotations provided, the description carries the full behavioral burden and does well: it discloses server-side computation, adjusted vs. nominal price handling, total-return inclusion rules when proventos exist, the absence of costs (with premissas returned), and the open/degustation access model. It does not describe output formatting or pagination, but for a computed-metric endpoint the behavior is well covered.

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 core purpose is front-loaded, but the passage is dense with parentheticals and shifting emphasis (adjusted price, total return, premissas, access model) that interrupt the main statement. It is informative rather than wasteful, but it is not as tightly structured as it could be.

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 6-parameter computation tool with no output schema and no annotations, the description supplies the defaults, the metric definitions, the price-adjustment and cost caveats, and the access/auth posture. The main remaining gap is date-parameter formatting for de/ate, which neither schema nor description addresses.

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 description coverage is 0%, so the description must compensate, and it does for the key cases: it defines the default period (últimos 5 anos), the moving-average defaults (21 × 100, matching media_curta/media_longa), and clarifies that chave_api is accepted but unnecessary. It doesn't add format guidance for 'de'/'ate' (the schema only gives empty-string defaults), leaving date syntax undocumented.

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 states a specific resource (performance of an AÇÃO over a period) in few numbers, naming the actual metrics (retorno, drawdown maximo with dates, volatilidade) computed for both buy-and-hold and a moving-average crossover. This is far more specific than the bare name 'desempenho' would suggest, though it doesn't explicitly distinguish itself from siblings like 'precos' or 'scores' by name.

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 an explicit when-to-use cue: 'Use esta ferramenta para "essa estratégia valeu a pena?" em vez de baixar a série diária,' which steers the agent away from the daily-price sibling. It also states the default period (5 years) and that no API key is needed. It stops short of explicitly naming an alternative tool, so a 4 rather than a 5.

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