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

Annotations declare the write/non-destructive/non-idempotent profile, and the description adds genuinely useful context beyond them: the version is published at the SAME URL, no HTML needs to be sent, card queries are re-run and charts redrawn, and every placeholder must be supplied. It stops short of describing what the response returns or version history behavior, but the bar is lower given the annotations.

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?

It front-loads the core action and the SAME-URL constraint, then enumerates the two operating modes. Dense but every clause carries information; a slight tightening of the parenthetical examples is possible but nothing is wasted.

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 4-parameter write tool with a nested `data` object and no output schema, the definition covers both execution modes, the required-data contract, and the natural use case (scheduled refresh). The only omission is what the tool returns / how the new version is identified.

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 coverage is already 100%, so the baseline is 3, but the description goes further by concretely explaining the `data` parameter's contract (flat placeholder->value map, every placeholder required) and giving a worked example including non-ASCII content. artifact_id and label semantics are left to the schema.

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 states a precise verb+resource — publishing a new version of an artifact at the SAME URL — and then splits the resource into its two concrete subtypes (analytics-card-driven vs. template-driven), naming the related artifacts_create/update operations. An agent can immediately tell this apart from artifacts_get, artifacts_list, or artifacts_update.

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 gives explicit conditional guidance: pass artifact_id alone for card-backed artifacts, pass data for template artifacts, and 'Ideal for a scheduled refresh of live numbers.' This routes the agent well, though it never explicitly states when to prefer artifacts_update over refresh or lists exclusions.

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