Update portal config

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

Annotations indicate readOnlyHint=false, destructiveHint=false, idempotentHint=true, and openWorldHint=true. The description adds significant behavioral context: it explains the write requires confirm=true, the dry_run behavior, the merge vs replace semantics, and the revert mechanism via previous_at_path. It also discloses that invalid references are refused. This goes beyond the annotations, which are sparse, and provides the agent with critical safety and operational details. The only minor gap is not explicitly stating that the tool is idempotent, but the description's mention of merge and revert implies it.

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?

The description is a single paragraph but packs a lot of information. It front-loads the core action ('Set a value at a config path') and then covers key behaviors. It's not overly verbose, but it could be slightly more structured (e.g., bullet points) for readability. However, every sentence earns its place, and the information density is high without being redundant.

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?

Given the tool's complexity (5 params, conditional write behavior, revert mechanism), the description covers the essential aspects: prerequisites, dry_run, merge, revert, and error conditions. There's no output schema, so the description's mention of previous_at_path is crucial. The only minor omission is not specifying the exact response format beyond previous_at_path, but that's acceptable given the tool's nature. Overall, it's complete enough for an agent to use correctly.

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%, so the schema already documents all parameters. The description adds value by explaining the relationship between parameters: confirm must be true for writes, dry_run previews without writing, merge modifies behavior, and the response includes previous_at_path for revert. It also clarifies the path format (array of strings) and gives an example. This is more than the schema provides, so it earns a 4 rather than a baseline 3.

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 clearly states the tool's purpose: 'Set a value at a config path.' It specifies the resource (portal config) and the action (set/update), and distinguishes it from siblings like get_config and update_resource by focusing on config path manipulation. The description also mentions specific config keys (default_dashboard/theme_id) and the merge behavior, which adds specificity beyond the name.

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?

The description provides explicit conditions for use: requires admin writes enabled (PORTAL_ALLOW_ADMIN_WRITES=1) AND confirm=true, and mentions dry_run for previewing. It also notes that pointing at a missing record is refused, which is a clear constraint. While it doesn't explicitly name alternatives, the context of portal config vs resource updates is implied, and the conditions are specific enough to guide when to use this tool.

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