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

With no annotations, the description carries the full burden and delivers: preview writes nothing, only allowlisted facts are saved, raw commands are never stored, first report wins within an hour, identical retries do not rewrite, and the operation never creates a measurement, sends a reading, installs software, or creates a schedule. This is precisely the behavioral context an agent needs.

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?

Roughly 120 words, with the purpose front-loaded, followed by workflow, then side effects and output behavior. Every sentence adds non-redundant behavioral information; there is no filler or restatement of the schema.

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 5-parameter tool with a nested object and no output schema, the description covers the multi-phase workflow, idempotency, safety boundaries, and the preview return shape. It leaves minor gaps: the default save receipt when Accept is not text/plain and the behavior on duplicate submission are not described, but the schema fully documents all parameters.

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. The description adds procedural context for conferir (initially true, omit to save) and maps saidas to pasted step output, but it does not add essential parameter meaning beyond the schema; relatorio remains documented only in the 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?

The description states a clear verb and resource: preview or save the allowlisted discovery report for one device. It is distinct from generic environment CRUD siblings through the 'allowlisted discovery report' scope, though it never explicitly names an alternative sibling.

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 workflow: send terminal and saidas with conferir:true first to preview, then omit conferir to save when complete. It also states exclusions and retry behavior (first report wins, identical retries do not rewrite) and side-effect boundaries, so an agent knows exactly when and how to use it.

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