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

Annotations provide only readOnlyHint=false, idempotentHint=false, and destructiveHint=false, which is minimal. The description compensates fully by disclosing that nothing is stored, that specific permissions (grocery:cart, email:send) are required, that the first use of cart mode may prompt account connection, and that coupons mode can only match items on coupon so most items remaining unmatched is normal. This exceeds what annotations offer and gives the agent a complete picture of side effects and conditions.

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 long but every sentence carries essential operational information. It is front-loaded with the core action and the propose-first rule. While it could be formatted with bullet points for easier scanning, the density is appropriate given the complexity of the tool's modes and permissions. There is no redundancy or fluff, so it earns a high score, though slightly below perfect due to the dense single-paragraph structure.

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?

The description covers all aspects needed for correct usage: the action, the sequencing requirement, all send modes and their permissions, the exclusion parameter semantics, the recipe_ids provenance rule, and the fact that nothing is stored. It even anticipates common pitfalls like unmatched items in coupons mode. For a tool with this complexity and no output schema, the description is remarkably complete.

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?

Although the schema already provides detailed descriptions for all parameters (100% coverage), the tool description adds significant meaning beyond the schema: it explains the propose-first workflow that dictates how the 'mode' parameter must be used, clarifies the coupon matching limitation for the 'coupons' mode, and reinforces that recipe_ids must come from specific tools. This contextual guidance is not present in the schema and is essential for correct invocation.

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 clearly states the tool's purpose: composing a consolidated grocery list from 1-8 recipes and handing it off for shopping. It distinguishes itself from sibling tools like get_shopping_list or update_shopping_list by emphasizing the build-and-handoff nature. The verb 'compose' and resource 'shopping list' are specific and unambiguous.

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 provides explicit usage rules: always call with mode 'propose' first, show the user, then wait for explicit approval before using send modes. It lists each send mode with its conditions and permissions, and explicitly says 'NEVER propose and send in the same turn'. It also instructs that recipe_ids must be copied exactly from search_recipes or list_conceits results. This is comprehensive and leaves no ambiguity about when and how to use the tool.

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