graph_from_account

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

With no annotations, the description carries the full behavioral burden. It discloses the two operating modes and the fact that sample: true avoids needing AWS credentials — this is genuinely useful behavioral info. But it omits the output shape, any side effects, and doesn't explain what a 'scan' (SOFE) is, so it doesn't fully compensate for the absence of annotations.

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 main sentence is a clean single statement of function, and the additional note is directly relevant to parameter use. There's one unexplained acronym (SOFE) that could cause confusion, but overall the text is tight and well-structured.

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?

The description covers the key operational detail (sample mode vs. real scan) but leaves gaps: the 'profile' parameter is not explained, 'SOFE' is undefined, and there is no mention of output shape or error conditions. With no annotations at all, these omissions matter for an agent deciding how to call this tool.

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 0/0% — with no descriptions in the schema, the description's job is critical. It explains the sample parameter's behavior well (true = example graph, false = expect prior scan), but the profile parameter is never described. An agent cannot tell what 'profile' means beyond its name, which is a substantial gap.

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 verb and resource: 'Convierte un perfil AWS (scan) en un Architecture Graph v0.4' (converts an AWS profile scan into an Architecture Graph). This clearly distinguishes it from sibling tools like graph_from_terraform or graph_from_evaluation, which use different input sources. The output format and version are also specified.

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 gives clear usage context for the sample parameter ('con sample: true devuelve un grafo de ejemplo' without requiring AWS credentials, versus expecting a prior scan with sample: false). However, it gives no guidance on when to use this tool instead of its siblings (graph_from_terraform, graph_from_evaluation), which is the main vertical comparison the agent needs.

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