dense_text

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

Annotations already declare readOnlyHint=true. The description adds behavioral details: it returns the graph in dense sigil notation, supports truncation via budget, and with seed returns the activated neighbourhood. This provides useful context beyond the annotation, such as output behavior and scope.

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 two sentences with no wasted words. It front-loads the tool's essence and follows with usage instructions. Every sentence earns its place, making it highly concise and well-structured.

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 simplicity (2 optional params, output schema present), the description covers the main behavior and usage modes. It lacks explanation of 'dense sigil notation' but is otherwise complete for an LLM agent to decide when and how to invoke the tool.

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% with good param descriptions. The description adds context about truncation and neighbourhood, but largely echoes the schema. Since the schema already explains the parameters well, the extra value is marginal, placing it at the baseline 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 the tool returns a structural graph in dense sigil notation (entities, relationships, scopes) and positions it as the primary context tool for LLM navigation. It differentiates between seed and no-seed modes, but does not explicitly distinguish from similar sibling tools like graph_view. Hence a 4 for clarity but lacking sibling differentiation.

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 explicitly says it's the primary context tool for LLM navigation and explains when to use the seed parameter (scoped map) vs without (full graph truncated to budget). It provides clear context for use but does not mention when not to use it or list alternatives explicitly.

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