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

With annotations already declaring this is a non-read-only, non-idempotent, non-destructive write, the description adds real context: the required role, the fact that only new AI requests pick up the price, and the two distinct write modes. It still doesn't say whether setting a price overwrites an existing one or how conflicting fields are reconciled.

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?

Three sentences, no filler, with the primary behavior front-loaded and the discount variant clearly marked by 'or with model *'. The first sentence is dense enough that a bulleted split of the two modes would read faster, but nothing is padded.

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?

An output schema exists so return values need no explanation, and auth plus effect timing are covered. For a 9-parameter mutation with two disjoint modes and zero schema descriptions, the agent still lacks guidance on valid parameter combinations, the role of the required provider field, and overwrite semantics.

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 0% and the schema carries only titles, so the description must compensate, and it does partially: it explains the per-million vs per-unit split and the model='*' + discount_pct pairing. However the required 'provider' parameter, 'note', 'cached_input_per_million', and the mutual-exclusion rules between discount_pct and the price fields are never addressed.

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 (set the org's own price for a model) and spells out both operating modes: per-token pricing and the model='*' + discount_pct discount mode. It doesn't name which sibling to use instead (e.g. get_model_price for reading, list_your_prices for enumerating), so differentiation relies on the name alone.

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?

'New AI requests use it' hints at when the change takes effect rather than when to call the tool, and the admin/owner/finance requirement is a useful prerequisite. There is no explicit guidance on when not to use it or which sibling handles related tasks like reading existing prices.

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