vault_impact

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

With no annotations, the description carries the full load and does so well: it discloses the transitive-by-default behavior, quantifies how badly depth-1 understates impact (median 3.9x, up to 9.5x), and explains what each semantics mode follows ('Governed by' vs 'Read first'). It omits return format and cost/performance, but the behavioral core is genuinely disclosed.

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?

Front-loaded with a clear one-line purpose, then rationale and mode semantics. It is dense and jargony ('Governed by', 'framework note', the multiplier statistics), but each sentence carries information rather than filler.

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?

For a 3-param analytical tool with no output schema and no annotations, the description supplies the semantics of both meaningful parameters and the default behavior, enough to call it correctly. It does not describe the shape of the returned set, which an agent might want.

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 coverage is only 33% (note is undocumented; semantics has enum values but no description), so the description must compensate. It adds substantial meaning for semantics, distinguishing 'falsified' from 'needs_reread' by edge type and framing the resulting question, and clarifies deep implicitly via the transitive-vs-depth-1 contrast.

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 phrase 'blast radius of changing a note' states a specific resource and operation, and the transitive-vs-depth-1 discussion pins down exactly what is computed. It stops short of contrasting itself with graph-adjacent siblings like vault_neighbors or vault_load_bearing, so an agent must infer the difference.

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?

'Run before editing any framework note' is explicit when-to-use guidance scoped to a class of notes. It does not name an alternative tool or state exclusions (e.g., when depth-1 or neighbors is preferable), so it falls short of full routing guidance.

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