Context Graph

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

Annotations declare readOnlyHint=true, destructiveHint=false, idempotentHint=true, openWorldHint=true. The description adds context on output structure (nodes, edges, lateral_paths) and analysis type, without contradicting annotations. It does not detail permissions or side effects, but annotations already cover safety.

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 concise (three sentences), front-loaded with purpose, and well-structured. It efficiently conveys the tool's function, modeled entities, key question, and return fields with no extraneous content.

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 the tool's complexity and that an output schema exists (so return values need not be explained), the description sufficiently covers purpose, usage context, and output structure. It mentions all relevant return fields, making it 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 100%, so the schema already documents all three parameters. The description does not add additional meaning beyond the schema, resulting in a baseline score of 3.

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 builds an agent context graph for lateral movement analysis, with a specific verb and resource. It distinguishes from siblings like 'blast_radius' and 'exposure_paths' by focusing on reachability between agents, servers, credentials, tools, and vulnerabilities.

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 answering a concrete question, 'If agent X is compromised, what else becomes reachable?' but does not explicitly guide when to use this tool versus alternatives like 'blast_radius' or 'exposure_paths'.

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