form_perform_external_validation

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

Annotations already declare openWorldHint=true, idempotentHint=false, and destructiveHint=false, so the safety profile is covered. The description adds no behavioral context beyond repeating 'external': it does not say that validations are dispatched to configured external source providers, whether results are returned synchronously, or how failures surface. The only extra content is the raw endpoint path, which conveys little to an agent.

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 purpose sentence is front-loaded and short, but the second line is a bare POST path that adds no actionable meaning for a model, making the definition sparse rather than efficient.

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?

This is intentionally a placeholder – I will fill it in now: The tool has a nested required object body, external (open-world) behavior, and no output schema, so the description needs to explain payload construction and expected response. It covers neither, leaving the agent unable to assemble a valid request without reverse-engineering the 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 coverage is only 67% and the description contributes nothing about parameters: it never explains the required 'body', the 'context' map of field values/dataTypes, the 'externalValidations' array of label/source/target entries, or what sourceId vs projectId select. With a deeply nested required body, the description should compensate and does not.

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+resource ('Perform external validations for a form'), which is better than a tautology, but the qualifier '(for the UI)' adds ambiguity rather than scope, and nothing distinguishes it from nearby siblings like form_execute_external_action(s), form_get_external_value, or form_lookup_external_resources, which all sound related to external evaluation.

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?

There is no guidance on when this tool should be invoked, what must exist beforehand (a rendered form, an external source provider), or which sibling to prefer for adjacent external-value/validation needs. The agent must infer usage entirely from the name.

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