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

Annotations already cover the safety profile (readOnlyHint=false, idempotentHint=true, destructiveHint=false), so the bar is lower, yet the description still adds meaningful behavior: changes are persisted immediately on invocation and the reason string surfaces on a user-facing approval card. It does not explain whether omitted fields (text or gridPos) are preserved, which is the main remaining behavioral gap.

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 with the mutation scope front-loaded and the skill prerequisite last, where it reads as a pre-flight step. "Saved when this runs; explain it in reason" is dense but slightly telegraphic, and no sentence 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 5-required-parameter mutation with full schema coverage, no output schema, and annotations covering safety, the description is close to sufficient: scope, persistence, approval reason, and skill prerequisite are all present. The missing piece is partial-update semantics, i.e. whether passing only text leaves position and size untouched.

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 100%, including the grid sizing guide in gridPos, so the baseline of 3 applies. The description adds little beyond the schema, only reinforcing that text and gridPos are independently optional ("and/or") and that reason is user-visible, which the schema already states.

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?

"Change a section heading's text and/or position and size" gives a specific verb plus the exact editable fields of the resource, so an agent knows this mutates an existing heading rather than creating one. It never names add_heading_panel or update_markdown_panel, so the create-vs-edit and heading-vs-markdown distinctions are left to inference from the verb choice.

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 supplies a real procedural prerequisite (load the manage-dashboards skill first), which is more than most definitions offer. However it never states when to prefer this over add_heading_panel, update_markdown_panel, or update_dashboard_layout, nor what to do if the panel is not a heading.

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