set_stock_count

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

With no annotations, the description carries the full burden, and it does disclose one important operational fact: the write/apply path is currently gated behind an incomplete adapter and canary. It says nothing about permissions, idempotency behavior, what previewToken/expected*Hash preconditions do when violated, or what a preview returns, which is a substantial gap for a 10-parameter mutation tool.

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?

Two compact sentences with the core differentiator (preview-first) and the blocking constraint front-loaded. No filler, though both sentences spend words on replacement/deprecation history rather than on operability.

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 10-parameter, nested-object, hash-guarded, no-output-schema tool, this description is far too thin. It omits the preview-to-apply flow, the meaning of the three expected-hash guards, idempotency semantics, and required inputs, leaving the agent unable to construct a correct call.

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 0% across 10 parameters, so the description must compensate and it essentially does not. Only an indirect mapping exists ('Preview' ~ dryRun/previewToken, 'Apply' ~ dryRun=false); mode, values, idempotencyKey, expectedDesiredHash, expectedSemanticHash, expectedWriteShapeHash and expectedEntityTimestamp are entirely unexplained anywhere.

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 identifies the resource (stock-count write) and its distinguishing trait (preview-first, replacing the deprecated immediate write), so an agent can separate it from list_stock_counts/get_stock_count and from the legacy write path. It stops short of plainly stating what the tool produces, expressing its purpose relative to a predecessor and a deployment status instead, and never contrasts with the sibling upsert_stock_count.

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?

It gives one real usage constraint — apply is unavailable, so only the preview path is usable — which is genuine when-not guidance. However it names no alternative tool for actually committing a stock count (upsert_stock_count exists) and does not explain when a dry run vs. a commit should be chosen.

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