get_surprises

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

Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true. The description reinforces read-only behavior and adds return format details, including the JSON structure and the fact that it surfaces hidden coupling. No contradictions.

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?

Two sentences plus a return format line. Front-loaded with main purpose, no wasted words. Every sentence adds distinct value.

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 1 parameter, no output schema, and good annotations, the description is fairly complete. It explains purpose, prerequisite, and return format. Could elaborate on surpriseScore calculation, but not essential.

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?

Only one parameter (top_n) with 100% schema coverage. Description adds the default value (20) which is not in the schema's min/max, providing extra context beyond 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 clearly states it ranks cross-module file edges by unexpectedness, surfaces hidden coupling. Uses specific verb+resource ('Rank cross-module file edges'), distinguishing it from siblings like get_coupling or get_edge_bottlenecks.

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?

Explicitly states prerequisite: 'Requires detect_communities to have been run first.' This provides clear context for when to use. However, no explicit alternatives or when-not-to-use guidance.

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