get_promotions

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

The description goes far beyond the annotations: it discloses sorting order (most recent first), pagination limit (20 per page), server-side auth injection (model never handles tokens), rate limiting (30-per-10s cap), retry behavior on 429/5xx, and the exact error surface (401/403/404/422). It aligns with readOnlyHint=true by stating it 'creates, changes and deletes nothing.'

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?

The description is front-loaded with a '🟢 READ-ONLY · GET /v2/promotions' summary line and organized into labeled sections (Behavior, Parameters, Returns, Use when), which makes scanning easy. It is slightly verbose relative to the tool's single-parameter complexity, with minor redundancy against annotations and a somewhat long related-tools list, but every section earns its place.

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?

With no output schema, the Returns section correctly explains the response shape (HTTP status + LearnWorlds JSON body) and error payloads — essential information an agent would otherwise lack. Combined with pagination, auth, throttling, and usage guidance, nothing needed to invoke this tool correctly is 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?

Schema coverage is 100% and the schema already documents `page` with its default and out-of-range behavior. The description adds only light context ('results are paged — walk them with `page`'), tying the parameter to the 20-per-page limit, which is useful but not substantial beyond the schema. Baseline 3 is appropriate.

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 states a specific verb and resource: 'Get promotions. Returns a list with all the promotions of the school.' It adds scoping detail (all promotions, sorted by recency) and explicitly names sibling tools such as get_promotion, create_promotion, and create_coupon_promotion, so an agent can distinguish this list operation from singular and write variants.

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?

The 'Use when' section is explicit: 'safe to call speculatively for lookups and reporting. Not for changing anything — use the matching 🟡 write tool.' It names the write alternatives (create_coupon_promotion, create_coupons_promotion_bulk, create_promotion) and lists related Promotions tools, giving clear routing guidance with no ambiguity.

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