blast_radius

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

No annotations are provided, so this dimension carries full weight. The description explains the concept (downstream impact) but doesn't disclose specifics like whether it mutates state (it's a read/compute, likely safe), performance implications (deep graphs or infinite depth), or error handling. It mentions max_depth=None means infinite, which is a useful behavioral note. However, it doesn't state whether it's read-only or if there are side 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 moderately concise: a one-line summary plus an args list. It's front-loaded with the concept, then details params. Every sentence adds information. Minor redundancy: 'Downstream impact de un nodo' uses Spanish while the rest is English, which could be cleaner, but it's not verbose. The structure is clear and skimmable.

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?

Given it's a compute tool with 4 params, no output schema, and no annotations, the description covers the key behaviors: what it does, how to use it, and what the args mean. It lacks details on return format (downstream impact as what data structure?), but the description explains the concept enough for an agent. It could be improved by explaining what the output looks like, but it's reasonably complete.

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. It does explain each parameter in the docstring: node_id (id of origin node, example given), graph (graph JSON v0.4, output of graph_from_*), max_depth (max depth, None = infinite), rel_types (filter to these relType). This is solid, but it doesn't specify the format of graph beyond 'v0.4' or give example values for rel_types beyond 'invokes'. Minimal compensation for zero schema coverage.

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 purpose: compute downstream impact of a node (what breaks if it fails). It uses a specific verb ('compute'), resource ('node in a blast radius graph'), and gives a concrete example. It clearly distinguishes from siblings like graph_from_* (which build graphs) and validate_graph (which validates), so an agent can tell when to use this versus others.

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 usage by showing the graph is an output of graph_from_* functions, suggesting a workflow. It doesn't explicitly state when not to use it or name alternatives, but the arg examples ('node_id' like 'api', 'rel_types' like 'invokes') give clear context on how to call it. It could be improved by mentioning it relates to blast radius analysis only, but the context is mostly clear.

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