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

Annotations already declare the write-but-not-destructive, idempotent profile, so the description only needs to add context — and it does: 'Saved when this runs' tells the agent the change persists immediately with no preview or undo, and the reason field surfaces on a user-facing approval card, disclosing an approval gate. It stops short of saying whether content replaces existing text entirely or what happens to an omitted gridPos.

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: what it changes, what happens when it runs plus the reason requirement, then the prerequisite. Front-loaded and zero filler, with the skill prerequisite placed last where it does not obscure the core action.

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 7-parameter mutation with a nested gridPos object, full schema coverage, and an approval requirement, the description covers the action, the persistence semantics, the required justification, and the skill prerequisite. Remaining gaps — replace-vs-merge behavior on content and fallback for an omitted gridPos — are modest given the thorough schema.

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%, with content, gridPos sizing guidance, panelId provenance (from get_dashboard), and project/environment discovery all documented in the schema itself. The description only adds a pointer to the reason field, which the schema already explains as the approval-card sentence. Baseline 3 is appropriate when the schema carries this much weight.

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 names a specific verb and resource ('Change a markdown panel') and scopes it precisely to 'text and/or position and size', which maps directly onto the content and gridPos parameters. It does not explicitly contrast with siblings such as add_markdown_panel, update_heading_panel, or update_dashboard_layout, so the update-vs-create distinction is only implied by the verb.

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 a concrete workflow prerequisite: load the manage-dashboards skill via load_skill("manage-dashboards") before calling. It also tells the agent what must accompany every call ('explain it in reason'), but it never names an alternative tool or a condition where a different tool should be chosen instead.

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