get_surprises

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

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds 'Read-only' consistent with that, and explains the output structure (JSON with edges and totalCommunities). It also reveals the 'surprise' definition, adding behavioral context beyond the 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?

Two highly informative sentences: first explains purpose and criteria, second states prerequisite and output. No excess words, front-loaded with key 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?

Given one parameter and no output schema, the description adequately covers prerequisite, output format, and the concept of 'surprise'. It could elaborate on how surprise is computed, but the current level is sufficient for agent decision-making.

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?

The only parameter (top_n) has schema description covering 100%, so the description adds no extra meaning beyond the schema. The description mentions ranking but doesn't link to the parameter, keeping at baseline.

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 defines the tool's purpose: ranking cross-module file edges by unexpectedness based on deep folder distance, popular target, and few edges. It distinguishes from siblings like get_coupling by focusing on 'surprises' that reveal hidden coupling, and the specific criteria are stated.

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 a prerequisite (detect_communities must be run first) and describes the use case (surfacing hidden coupling for shotgun changes). However, it does not mention when not to use this tool or name alternative tools for related analyses.

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