calculate_spectrum

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It meaningfully discloses an edge case: returns None per region when the graph has fewer than 4 nodes, and emphasizes that it never returns an invented embedding for a too-small graph. This is valuable beyond what the schema conveys, though it does not discuss other behavioral aspects like read-only status or parameter effects.

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 is reasonably concise, front-loading the core purpose and then covering the small-graph edge case. The phrase 'nunca un embedding inventado para un grafo demasiado pequeño' is slightly repetitive after the None explanation, but overall every sentence contributes useful information.

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 explains the output shape and an important null-behavior, and an output schema exists so return values do not need further elaboration. However, it does not explain the two optional parameters or provide explicit selection guidance relative to sibling tools. For a three-parameter tool with 0% schema coverage, this leaves some gaps.

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 for the lack of parameter explanations. The description clarifies that the tool works on 'the real graph of an atlas' and that the output relates to graph structure, which helps slightly with atlas_id. However, min_weight and connection_type are completely unexplained, and their roles in constructing the graph are left to the agent to infer.

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 identifies the tool's output as a 2D spectral embedding (Laplacian eigenmaps) of an atlas's real graph, with one position per region. It distinguishes this from anatomical-position-based tools by saying it is useful for seeing groupings without depending on anatomical position. It does not state an explicit verb like 'calculates', but the noun phrase 'Embedding espectral 2D' is specific enough to convey the action.

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 implies when to use the tool: when wanting to see clusters derived from graph structure rather than anatomical position. However, it does not explicitly mention when not to use it or name alternatives such as calculate_laplacian or render_network. The guidance is implied but not fully articulated.

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