update_dashboard

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

Goes well beyond the annotations by disclosing a fetch-then-stash undo mechanism ('Captures the prior model for undo', 'stashed so the harness records a restore undo') and the uid prerequisite. This tells the agent the operation is reversible, which the destructiveHint=true annotation alone cannot convey.

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?

Front-loads the write/risk tags and the core action, then lists args compactly. The undo behavior is stated twice ('Captures the prior model for undo' and 'stashed so the harness records a restore undo'), a minor redundancy in an otherwise tight definition.

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 destructive 4-param mutation of a nested dashboard object with no output schema, the description covers the critical mechanics (uid requirement, undo capture, dry_run, overwrite). It does not address permission/authorization needs or failure behavior, and the nested dashboard model's internal structure is only partially sketched.

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 0%, so the description carries the full burden and does so for all four params: dashboard (full model, must include uid), overwrite (default True, overwrites existing version), dry_run (preview only), and target (Grafana target name from config, omit for default). Each parameter's meaning is clarified beyond the bare 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?

States a specific verb and resource ('Update a Grafana dashboard') and prefaces it with [WRITE][risk=medium] severity tags. Easily distinguished from siblings like get_dashboard, list_dashboards and delete_dashboard without opening any 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?

Gives clear operating context: the dashboard model must carry its uid, the prior model is fetched and stashed for undo, and dry_run lets you preview without updating. It does not explicitly name an alternative tool or spell out when-not to use it, but the write-vs-read boundary is unambiguous.

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