where_used

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

With no annotations, the description carries the behavioral burden and does so reasonably: it discloses the traversal direction, the edge semantics (lid depends_on housing), the output shape, and an important failure mode ('an unknown item fails loudly, never a silent empty set'). It doesn't cover permissions or performance on large graphs, keeping it below 5.

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?

Structure is front-loaded with the purpose, then parameters, then return shape, and each sentence earns its place. It is a bit dense with cross-references (issue #142, C3, §9) that don't help an agent, slightly reducing efficiency.

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-parameter tool with no annotations and only an inline return-shape note, the description covers purpose, the lockfile item/handling of unknown items, the meaning of direct, and what comes back. Nothing essential for correct invocation is missing.

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 0%, so the description must compensate and largely does: it explains that lockfile is the JSON assembly_lock wrote, that item is the component id to query, and that direct surfaces the immediate-neighbour layer. The direct flag's effect ('surface only the immediate mates separately') is what the schema alone would never convey.

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 verb (traverse the depends_on graph and report parents that consume an item) and clearly names the resource (lockfile dependency graph). It explicitly defines the semantics as 'reverse reachability' versus the lockfile's forward 'consumer -> consumed' edges, making it distinguishable from any graph-editing or assembly-tool sibling.

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 gives a clear usage context: impact/blast-radius analysis so that exactly those parents re-dispatch when an item changes. It implies when to use it, but doesn't name a concrete alternative tool from the large sibling set (e.g., change_impact, assembly_lock_check) or state exclusions.

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