remediation_plan

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions the output (IaC steps) but says nothing about whether the tool is read-only, its performance, or how the `graph` parameter influences execution. It leaves open whether invoking this tool has side effects, which is notable for a plan generator.

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 description follows a compact docstring format, leading with a one-line purpose followed by structured Args. It stays short but loses a point for mixing Spanish and English and not restating the `graph` default that appears in the schema, which could confuse non-bilingual agents.

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 2-parameter tool with no annotations or output schema, the description covers the essentials. However, it omits the exact structure of the returned plan (beyond 'pasos IaC'), whether an empty findings list returns an empty plan, and whether there's a limit on findings size. These are meaningful gaps given the bare schema and absent output schema.

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?

Despite 0% schema coverage and untyped properties in JSON Schema, the description fully documents both parameters: `findings` gets a clear JSON example with structure hints, and `graph` is marked optional with a version note. This precisely compensates for the lack of schema descriptions, making the tool callable incorrectly impossible for a careful agent.

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 clearly states the action ('Genera un plan de remediación') and the resource ('findings'), with a concrete output (IaC steps with Terraform snippets). It doesn't explicitly differentiate from siblings, but the tool name and description make its role unambiguous next to graph/schema-oriented siblings.

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 explains what the tool does but gives no guidance on when to use it versus alternatives like `blast_radius` or `validate_graph`. There are no preconditions, exclusions, or hints about when the optional `graph` parameter should be provided, so agents must infer usage from context.

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