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

Annotations already mark destructive and idempotent; the description adds that prior versions stay restorable within retention, that the operation is auditable, and that the publishing agent must manually author four narrative sections. This is valuable operational context beyond the annotations, with no contradiction.

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 short sentences each add distinct information: purpose/recoverability, retention behavior, and the narrative-writing requirement. No filler or redundant restatement; the most important fact is front-loaded.

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 destructive mutation with no output schema, the description omits critical invocation details such as how expectedProjectVersion is used (optimistic concurrency), what idempotencyKey enforces, and what the response indicates. The retention and narrative guidance help, but an agent could still misuse the required parameters.

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 description gives meaning to changeNarrative by specifying four plain-language sections, matching the schema's nested required fields. However, the four other parameters (projectId, expectedProjectVersion, idempotencyKey, sessionId) are left entirely undocumented, and with 0% schema description coverage the description only partially compensates.

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 opening sentence names the exact operation—'Reset the published graph to empty'—with a specific verb and resource, and the phrase 'explicit, auditable operation' clarifies its distinct role compared to incremental patch or publish tools. It does not name sibling tools, but the reset-to-empty semantics are unambiguous.

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 are no explicit when-to-use or when-not-to-use statements, and no alternatives are mentioned. The notes that prior versions remain restorable and that the publishing agent must craft the narrative imply a deliberate, safety-conscious reset, but selection criteria relative to patch_project_graph or publish_project_graph are left to inference.

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