Context Graph

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

Annotations already declare readOnlyHint, destructiveHint, idempotentHint, and openWorldHint, so the base level of transparency is established. The description adds value by detailing the return format (nodes, edges, lateral_paths, etc.) and the core behavioral focus on lateral movement, which is consistent with 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?

The description is appropriately sized: a one-line summary, a brief functional paragraph, and a bullet-like list of return fields. It is front-loaded with the main purpose. A minor improvement could be removing redundant phrasing, but it is efficient.

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 presence of an output schema (not provided but noted as true) and comprehensive annotations, the description covers the essential aspects: purpose, what it returns, and a usage example. It does not cover error handling or edge cases, but for a read-only, idempotent tool, this is acceptable completeness.

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?

All three parameters have descriptions in the input schema (100% coverage), so the description does not need to add much. The description does not mention parameters at all; it relies on the schema. The baseline score of 3 is appropriate because the schema already explains config_path, source_agent, and max_depth adequately.

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 tool builds an agent context graph with lateral movement analysis, specifying the resources modeled (agents, servers, credentials, etc.) and the concrete question it answers. This distinguishes it from siblings like 'blast_radius' and 'exposure_paths' by focusing on lateral movement reachability.

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 via the example question but does not explicitly state when to use this tool versus alternatives, nor does it provide exclusions or prerequisites. Siblings exist (e.g., 'blast_radius') that could overlap, and no guidance is given for choosing among them.

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