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

Beyond repeating the read-only annotation, the description contributes real behavioral context: the required scope (sites:read), the fact that target is null when no delivery exists, and that the returned version gates subsequent writes. It still doesn't describe output shape or error conditions, but the added auth and null-behavior notes are substantive.

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?

A single dense sentence front-loaded with the safety statement, then the resource and returned fields in a logical order. No filler or redundancy beyond the brief read-only restatement.

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?

There is no output schema, so the description carries the return-value burden, and it does list the key fields including the nullable target. It stops short of explaining sheets_mode values or the exact semantics of the version field, leaving a small gap for a config-read tool.

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?

With two parameters at 100% schema description coverage, the schema already documents both site and form. The description adds nothing about parameter format or cross-references beyond the schema's own hints (list_forms / list_sites), so the baseline 3 applies.

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 concretely enumerates what is returned for a form's Google Sheets delivery: spreadsheet, tab, status with paused_reason, required version, and sheets_mode. It is specific about the resource, though it never uses an explicit 'get/retrieve' verb and never mentions the sibling sheet_target_pause, so sibling differentiation is left implicit.

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?

Usage is only implied: read the Sheets delivery config for a given form. There is no statement of when to call this versus sheet_target_pause or other form-config reads, and no prerequisites or exclusions are given.

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