sb_store

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

Annotations only declare readOnlyHint=false, openWorldHint=true, destructiveHint=false; the description adds substantial behavioral context the annotations cannot convey — the fixed execution order, that checkout 404s without all four steps, that forms 'keep the options they were saved with', that overlay_attach/detach 're-read the page afterwards as the editor must', and that dry run returns the plan. It stops short of describing auth requirements or failure modes beyond the 404 case.

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?

Front-loaded with the core constraint ('must happen in a fixed order') and near every clause delivers actionable, non-redundant detail. It is a single very dense paragraph with no structural breaks per action, which costs some readability against the 17-parameter surface it documents, but there is little filler.

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-action dispatcher with no output schema, the description covers every action's effect, ordering constraints, the dry_run return, and the cross-tool relationships (sb_review) an agent needs to choose correctly. Nothing essential for correct invocation appears missing.

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 17 parameters at 65% schema coverage, the description carries real weight: it explains that overlay_id omitted creates from the platform seed, that global_id omitted on attach lists the site's own, the footer flag's meaning, relocalize's exact rewrite semantics, and which action each of kind/list_id/node_id/template/app_key belongs to. A few parameters (site_id, menu_id, headline, page_name, language) are left to the schema, hence not a 5.

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?

Each of the ten actions is given a concrete verb+resource pairing (e.g. checkout 'makes the order form... then creates and PUBLISHES the checkout page'; global_attach 'puts an EXISTING shared section on the open page'). It even differentiates from siblings in places (references sb_review's siteChrome gap, and contrasts chrome against global_attach). The density makes it slightly harder to parse than an ideal single-purpose definition, but the purpose of every action is stated.

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?

Explicit triggering conditions and alternatives throughout: checkout_sync should be run 'after adding a shipping method or switching on a gateway'; global_attach is 'the answer for a page that is missing the site's header, where action:"chrome" would wrongly build a second one'; cart is needed or 'every open_cart control opens nothing'. This is exactly the when/when-not/alternative guidance the dimension rewards.

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