project_graph

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

No annotations are provided, so the description carries the full behavioral burden, and it discloses almost nothing: no read-only confirmation, no scope (whole project? current workspace?), no return shape, no size or truncation limits. It also doesn't say what 'weighted' means concretely or how modules are resolved across languages. For a zero-annotation tool this is a substantial disclosure gap.

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?

A single tight sentence with no filler, and the core noun (dependency graph) is front-loaded. It is arguably under-specified rather than over-specified, but nothing in it is wasteful.

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 and no annotations, the description is the only source of truth about what comes back, and it gives just a phrase ('modules and weighted edges'). It doesn't state the scope of the graph, the direction of edges, the meaning of weights, or roughly how large a result to expect — all things an agent needs before invoking and parsing the result.

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?

The tool takes no parameters at all, so there is nothing for the description to disambiguate; baseline 4 applies. The description correctly avoids inventing parameter talk.

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 names a specific resource (module/package-level dependency graph) and states what it contains: modules and weighted edges between them. That is concrete and gives an agent a clear mental model of the output. It stops short of 5 because it never distinguishes itself from graph_stats, cross_language_edges, or impact_analysis, which all sit in adjacent territory.

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 indication of when to reach for this tool versus graph_stats or impact_analysis, and no note on prerequisites or cost. The agent must infer usage entirely from the resource noun. Only the implicit 'it's a graph' framing gives any selection signal.

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