graph_dependencies

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safe-read profile is covered. The description does add output-structure context (candidate vs confirmed edges reported separately), which is useful and not present in annotations, but it says nothing about scope (whole project vs. a node), ordering, or how the two groups are returned.

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?

One short sentence with no filler, and the most decision-relevant detail (candidate vs confirmed separation) is front-loaded. It is bordering on too terse for a graph-inspection tool, but nothing is wasted.

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?

With no output schema, the description carries the burden of explaining what is returned, and it only partially does so: it names the two categories but not the edge fields (source, target, type, certainty) an agent would need to consume the result. For a read-only list tool with fully documented params, this is adequate but with clear gaps.

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% and both parameters (project, workdir) are documented in the schema. The description contributes no parameter meaning at all, not even which project/workdir the listed edges belong to, so the baseline 3 applies.

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?

States a specific verb+resource (list dependency edges) and adds a meaningful qualifier: candidates (direction unconfirmed) are reported separately from confirmed edges. This distinguishes it in spirit from the sibling graph_depend (which implies creating/depending), but the description never names graph_depend, graph_show, or graph_node, so an agent must infer the boundary from the plural name alone.

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?

There is no when-to-use guidance, no prerequisites, and no mention of alternatives. The description never says to use this instead of graph_show or graph_node when inspecting the dependency graph, so selection among the closely-named graph_* siblings is left entirely to inference.

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