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

Annotations already declare destructiveHint=true, readOnlyHint=false, and idempotentHint=true. The description adds real value beyond them by disclosing recoverability ('Prior versions stay restorable within retention') and the manual changeNarrative obligation, which the annotations do not convey. It does not detail post-reset state or side effects on sessions.

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 tight sentences, front-loaded with the core action and no redundant restatement of the name. Each sentence carries distinct information (action, recoverability, narrative requirement), though the split could be slightly tighter.

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 full annotation coverage and no output schema, the description supplies the key operational facts: it is explicit/auditable, recoverable within retention, and requires a manually authored four-part narrative. Missing only auth/permission requirements and the exact post-reset state.

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 80%, so the baseline is 3; projectId, sessionId, idempotencyKey, and expectedProjectVersion are documented in the schema. The description adds only marginal meaning for changeNarrative ('four plain-language sections, manually written') without explaining what each section should contain, so it does not fully compensate for the undocumented parameter.

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 gives a specific verb+resource: 'Reset the published graph to empty,' which is distinct from publish_project_graph, patch_project_graph, and export_project_graph. It stops short of explicitly naming a sibling alternative (e.g., restore_project_version), but an agent can still distinguish the reset-to-empty action.

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?

It frames the call as 'an explicit, auditable operation' and notes prior versions remain restorable, which hints at intent, but there is no explicit when-to-use/when-not guidance or routing to alternatives like restore_project_version. Usage is implied rather than stated.

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