tela_descrever

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

With no annotations, the description carries the full behavioral burden, and it does disclose one meaningful trait: the image never reaches the caller, only a textual description produced by a local vision model. It omits other operationally relevant facts such as capture scope (whole desktop vs. focused window), latency, or whether an active/visible screen is required.

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?

Two short statements, front-loaded with the core action and followed by the parameter meaning. The line break and quoted parameter line are slightly awkward but nothing is wasted; it could be tightened into a single sentence without loss.

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?

An output schema exists, so return-value explanation is rightly omitted, and the single-parameter surface is small. What remains underspecified is the capture target — the family of siblings suggests window-level and browser-level reading tools exist, so knowing whether this captures the whole screen or a focused window matters for correct 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 0%, so the description must compensate, and it does: it explains that "pergunta" is what the agent wants to know about the screen and supplies a concrete example. It does not state that the parameter is optional with an empty default or describe behavior when it is omitted.

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-and-resource pair: takes a screenshot and has a local vision model describe it as text. The parenthetical "nenhuma imagem para você" usefully clarifies that the caller receives a description, not pixels. It does not, however, contrast itself with visual-reading siblings such as janela_ler or navegador_ler, so an agent must infer the distinction.

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 "pergunta" line implies the usage pattern — ask a targeted question about the screen — and the example ('apareceu alguma mensagem de erro?') reinforces it. There is no explicit when-to-use versus when-not guidance and no mention of alternatives like janela_ler for reading a specific window's text.

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