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

Annotations only declare openWorldHint=false and destructiveHint=false, so the description carries most of the behavioral load and does so well: it discloses that a plan subsumes everything below it, that lower-plan buyers upgrade for the price difference, and that a folder's code is "left out of the other plans' code" — a side effect on sibling plans. It also warns against inventing prices, which is an important agent-behavior constraint; only auth requirements and post-creation effects on the renamed base plan remain unstated.

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?

Purpose and ordering are front-loaded, and nearly every clause carries new information about ordering, upgrade credit, base plan naming, code sourcing, or pricing etiquette. The prose is dense and occasionally tangled — "It includes everything below it, so it costs more than every plan below it" is near-circular — but no sentence is 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 nested ten-field creation call with no output schema and thin annotations, the description covers the conceptual model (tiered plans, upgrade deltas, base plan naming, code provenance) that the schema alone cannot convey. Gaps remain around slug, the plan description field, subscription interval semantics, and what is returned on success, but none block correct invocation.

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 50%, so the description must compensate, and it does for the hard parameters: repository_id, source_url and folder are explained as mutually alternative code sources, base_plan_name is tied to the first-plan rule and to later renaming, and the price fields are framed relationally (must exceed the plan below). It adds little for slug or the nested context object, and the price guidance duplicates schema text somewhat.

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?

"Adds a plan to one of the user's listings, above its others" gives a specific verb plus resource and immediately establishes the ordered-plan concept that separates it from update_plan and remove_plan. Sibling names are not called out explicitly, so an agent must infer from the verb alone that this is the creation path, but the purpose is unmistakable.

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 description supplies real conditional rules: "The listing's first plan names its base plan too", "While the listing sells updates, each plan needs an updates price too", and "Never set its prices yourself; ask the user." These tell the agent when certain fields are required and impose an escalation behavior, though there is no explicit when-not clause or named alternative for revising an existing plan.

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