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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the bar is lower. The description adds genuine behavioral context beyond that: it aggregates all rejections, dangling-edge warnings, and unscored statuses in a single call rather than failing fast, and confirms no version is published — useful since no output schema exists.

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?

Two tight sentences with no filler; the dry-run identity is front-loaded and the return behavior follows immediately.

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 partially carries return-value burden by naming the categories of findings. However, it omits the large-array param semantics (maxItems of 5000/15000) and the erroneous/duplicated sessionId description is left unaddressed, leaving gaps for a complex validation tool.

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 only 50%, and the two documented fields (projectId, sessionId) already carry their descriptions in the schema. The description never explains the required nodes and edges arrays or their inner fields (id, status, sourceId/targetId, etc.), so it does not compensate for the coverage gap.

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 and resource ('dry-run graph acceptance') and clarifies scope ('without publishing a version'), which implicitly separates it from the publish_project_graph sibling. 'Acceptance' is slight domain jargon, so it stops short of a fully self-evident 5.

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 dry-run framing plus 'without publishing a version' makes the usage context clear: this is the pre-publish check rather than the publishing action. It stops short of naming publish_project_graph explicitly or stating exclusions, so it is clear context but not full when/when-not guidance.

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