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

With no annotations, the description carries the burden and does disclose security constraints (never send a secret key), a business rule ('only visit counts toward the chart'), a leniency rule ('legacy attempt accepted'), and partial return info (the reply includes basis and counts_toward_chart). It omits the dry_run behavior and any failure/validation-error semantics, which is the main remaining gap.

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?

Information is front-loaded correctly (purpose, then requirements, then optionals, then tips), but it is delivered as a single dense run-on paragraph mixing tag syntax, enum lists, and operational advice. Nearly every clause earns its place, yet bullet-style grouping of the enum values would make it far more scannable.

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 nested-object event tool with no output schema and no annotations, the description covers the critical validation vocabulary and even previews two reply fields. It falls short only on the unexplained dry_run flag and on what a rejected event looks like.

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 only describes the event blob and leaves the tag vocabulary entirely implicit (0 formal enums), and the description compensates heavily by spelling out the store tag formats, all valid depth values, basis values and their default, and the amount variants. The cost is that dry_run is never mentioned anywhere, leaving one of the two parameters undocumented.

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 and resource ('Submit a kind 422 shopping-experience note or review') plus the precondition that it must already be signed locally. This distinguishes it from build_experience_note, which is named as the tag-construction step, though the description never explicitly contrasts the two in one clause.

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?

Gives a clear workflow: build tags with build_experience_note, sign locally, then submit here, and warns 'never send a secret key.' It also says a store tag and depth-or-rating are required, which amounts to preconditions. It does not state when NOT to use it or what happens on rejection.

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