neighborhood

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

Annotations already declare the tool read-only, idempotent, and non-destructive, so the description does not need to repeat those. It adds algorithmic context (1-hop expansion, token budget) and clarifies the input mechanism (seed and anchors), which is useful. However, it does not disclose limitations, edge cases, or what happens when the budget is exceeded, so it adds only moderate value 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?

The description is a single, focused sentence with no fluff. It front-loads the core action and constrains the scope. Every word carries meaning, making it highly efficient for an agent to parse quickly.

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 (graph traversal with a budget) and the presence of an output schema, the description does not need to detail return values. However, it is missing key contextual details: what qualifies as a 'hard edge', how the token budget is allocated, and how 'as_of' fits into the operation. These gaps could lead to incorrect invocation, making the definition only minimally adequate.

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?

With 0% schema description coverage, the description must explain parameters. It does clarify that 'intent' is the seed, 'anchors' are explicit anchors, and 'budget_tokens' is the token budget. However, it neglects 'as_of' entirely and uses jargon ('hard edges') that isn't defined. Thus it covers most but not all parameters, and only partially compensates for the schema's lack of descriptions.

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 states a specific purpose: expanding hard edges one hop from an intent search seed and explicit anchors to produce writing context packets within a token budget. It clearly identifies the verb ('expand'), the resource ('hard edges'), and the output ('context packets'), distinguishing it from siblings like trace or graph_schema.

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 explains what the tool does but provides no guidance on when to use it instead of alternatives such as trace, query, or graph_schema. It does not mention conditions, exclusions, or scenarios where another sibling would be preferred. The implied use case (gathering neighboring context) is present but not explicit.

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