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

Annotations already declare readOnlyHint=false, idempotentHint=true, destructiveHint=false, so the safety profile is covered. The description adds genuinely new behavior: the change propagates to every dashboard displaying the query, the change is persisted ('Saved when this runs'), and the reason surfaces on an approval card. It stops short of saying what happens on a name collision or whether both fields can be changed in one call.

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 load-bearing: scope of the edit, the routing rule to alternatives, and the skill prerequisite. The most important constraint (what this tool does not do) is front-loaded right after the purpose.

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 6-parameter mutation with no output schema, the description covers purpose, scope of effect, persistence, required rationale, and the prerequisite skill. Remaining gaps are edge-case behavior (partial updates, name conflicts, error shape), which are minor but would be useful for a write 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 coverage is 67%, with queryId, projectId, environment and reason already documented in the schema. The description maps 'rename' to the name field and 'change its description' to the description field, which is mild added meaning, but it says nothing extra about the three id/scoping parameters or the length limits. Baseline 3 is appropriate when the schema does most of the work.

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 precise verb pair and resource: 'Rename a saved analytics query or change its description,' plus the propagation scope 'on every dashboard that shows it.' It explicitly names the sibling tools it is not (update_insight_query / update_funnel_query / update_retention_query / update_heatmap_query), so an agent can separate metadata edits from definition edits without opening a schema.

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 an explicit when-not rule ('To change what it measures, use update_insight_query / ... instead') with named alternatives, and a prerequisite ordering ('Load the manage-dashboards skill ... first'). Nothing about tool selection is left to inference.

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