Create a resource record

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

The annotations already indicate readOnlyHint=false and destructiveHint=false, but the description adds crucial behavioral context: writes are gated by risk domain, and there is a dry_run parameter to test without creating. This enriches the agent's understanding of the tool's behavior beyond what annotations convey. However, it does not explicitly mention idempotency (which the annotations say is false) or what happens on validation failure, but the dry_run mention partially covers the validation aspect.

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 two sentences, both packed with essential information. It front-loads the core action and then immediately gives the most critical usage constraint (write gates). No filler words. Perfectly sized.

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 (three params, one with enum, nested body, write gating), the description covers the key aspects: what it does, how to use it (dry_run), and when it's allowed. It lacks explicit return format, but there is no output schema, so the description should ideally mention what the response contains. However, the description's mention of 'report the would-be write' for dry_run gives some hint. It also doesn't list which resources are admin vs data, but that's covered by the environment variables. Overall, nearly complete.

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?

The schema provides descriptions for all three parameters (body, dry_run, resource), with resource having an enum and clear description. The description adds value by explaining that `body` carries fields and that dry_run runs all gates, but largely repeats what the schema says. Since schema coverage is 100%, the description doesn't need to add much, but it does provide a little extra context about the write gates.

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 verb ('Create') and the resource ('record'), and mentions that `body` carries the resource's fields. It distinguishes from siblings like create_block and update_resource by being a generic create. However, it does not explicitly differentiate from create_block, which could be a specific case of create_resource.

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 explicitly states the gating conditions by risk domain: content writes are on by default, while data and admin writes require specific environment variables (PORTAL_ALLOW_DATA_WRITES, PORTAL_ALLOW_ADMIN_WRITES). This tells the agent when it can and cannot use the tool, and implies that for admin/data resources it may need to check permissions first. It also references describe_resource for details, which is helpful.

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