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

Annotations already declare non-read-only, non-idempotent, non-destructive, closed-world, so the bar is lower. The description still adds real value: the exact request shape and endpoint, the no-reservation guarantee, unknown-SKU rejection, and that an insufficient balance fails without deducting credits — all non-obvious failure semantics.

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?

Five short sentences, front-loaded with the core action and credit implication, then progressively narrower caveats. Each sentence carries distinct information — mechanism, endpoint, return, exclusion, error behavior — with no repetition of the title or schema.

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 description covers the return ('returns that JSON, including the pack or recipe payload') and the auth story is handled in the schema, so an agent has enough to call it. It stops short of stating retry/idempotency consequences of a failed or repeated purchase, which is the one remaining gap for a spend-credits operation.

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%, so sku and api_key are already fully documented, including the sku-vs-sku_id warning and the BOTSUPPLY_API_KEY fallback. The description only restates that sku is the sent body field, adding no format or constraint detail beyond the schema, so the baseline 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?

States a specific verb (buy) and resource (one live catalog SKU) with the exact credit mechanism and endpoint (POST /v1/purchase). The scope phrase 'one live catalog SKU' cleanly separates it from list_catalog, create_checkout, and get_balance without needing to open any schema.

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 rules out adjacent behavior ('Does not place a reservation') and clarifies that recipe.book-table is documentation the caller runs itself, which prevents a mistaken tool call. However it never states when to choose this over siblings like create_checkout, so the when-to-use decision is only implied by the word 'buy'.

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