fl_apply_verified_batch

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

Annotations already mark this as a non-read-only, destructive, non-idempotent call. The description adds 'without replay', but doesn't say what a closed-union application does to existing state, when writes are committed, or what happens on unverified items — especially important for a destructive tool whose schema includes stop_on_unverified and per-item receipts.

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?

One front-loaded sentence with no filler or repeated schema information. Every clause ('closed-union', 'after one session preflight', 'without replay') is attempting to convey a distinguishing property rather than padding.

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, non-idempotent batch writer with 23 operation discriminated union variants, this one-sentence description is thin. It doesn't connect the batch to the required preflight step by name, explain what 'verified' means, or indicate how failures are handled; the rich schema and output schema carry most of the burden.

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%, and the operations parameter's own description adds crucial semantics (ordered absolute writes, unique operation IDs and written fields, per-item receipts). The tool description itself contributes no parameter-level information, so the baseline of 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 names a concrete action ('Apply') and object ('a closed-union batch') and adds two meaningful qualifiers: it happens after a single session preflight and without replay. This is more than a restatement of the tool name, but the jargon terms 'closed-union' and 'preflight' are not decoded, and no sibling tool is named, so it stops short of full clarity.

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?

'After one session preflight' implies a precondition and suggests this is the bulk-write counterpart to a preflight read, so the usage context is weakly signaled. However, it gives no explicit when-not guidance and does not name the individual fl_set_* setters or apply_plan siblings it should be preferred over or combined with.

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