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

Annotations already mark the operation destructive and idempotent. The description adds concrete behavioral facts: removing a node detaches its edges, the result reports exactly what was applied, and the changeNarrative must be manually authored. It stops short of stating what happens on a version mismatch, but the added context goes well beyond the annotation baseline.

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?

Three sentences front-load the core purpose, then add two crucial behavioral details and one procedural requirement. No filler or repetition; every sentence earns its place.

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 10-parameter destructive mutation without an output schema, the description provides the essential operation model, side-effect, and result-reporting guarantee. It leaves out the failure mode for a stale expectedProjectVersion, preconditions about whether a published graph must already exist, and the shape of the reported result, so an agent still has to infer some contract details.

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 carries the burden of explaining parameters. It clarifies that upsertNodes/upsertEdges are upserts, removeNodeIds/removeEdgeIds are removals, expectedProjectVersion is the concurrency guard, and changeNarrative has four hand-written sections. Many parameters (idempotencyKey, sessionId, mappedRevision, nested node fields) remain unexplained, so compensation is only partial.

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 opens with a specific verb ('Apply') and resource ('bounded delta to the published graph'), and names the exact operations (upserts, removals) and the version-check condition. This distinguishes it from siblings like publish_project_graph (full publish) and clear_project_graph (bulk clear).

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 implies usage context—a delta against a published graph with a version check—and tells the publishing agent to supply the changeNarrative. However, it never explicitly states when to use this over publish_project_graph, clear_project_graph, or other graph tooling, nor does it name alternatives.

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