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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower, and the description adds real information beyond them: results are expectations multiplied by a chance factor, not guaranteed outcomes, and are broken down both per input and in total. It does not discuss unknown/unrecyclable items or how the two recycler tiers differ quantitatively, leaving a modest 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?

Two short sentences, with the core purpose front-loaded and the output shape second — no filler. The opening sentence duplicates the title verbatim rather than adding information, a minor wasted line in an otherwise tight definition.

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 two-parameter, fully described read-only schema with no output schema, the description supplies the missing piece: what the response contains (per-input and total expectations inflated by chance). It stops short of covering edge cases such as invalid shortnames or non-recyclable items, which an agent would otherwise discover only through errors.

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 100% and both parameters already document their format and enum meaning, so the baseline is 3. The description reinforces that `recycler` changes the yields ('for the chosen recycler') but adds no syntax, defaults, or interpretation guidance beyond the schema.

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 names a specific computation (expected recycling yield) applied to a specific resource (a list of items) with a scoped modifier (the chosen recycler). Sibling tools like calculate_craft_cost and calculate_raid_cost make 'which calculator' the key ambiguity, and the recycling framing plus the 'quantity x per-unit yield x chance' formula resolves that implicitly. It never names an alternative calculator explicitly, which keeps it out of 5 territory.

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?

Usage is only implied: an agent can infer this is the tool for recycling math, but there is no statement of when to prefer it over calculate_craft_cost or calculate_raid_cost, no prerequisites, and no note about what to do if an item is not recyclable. The required `items` format is delegated entirely to the schema.

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