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

Annotations only declare destructive/non-idempotent; the description goes far beyond by disclosing the 409 refusal condition, the fact that the first call writes nothing, that a 'confirm' boolean is silently ignored, and that the token expires in 5 minutes and is single-use. These are exactly the failure modes an agent would otherwise hit.

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?

Front-loaded with the permission requirement and core action, then escalates to the risk details in a sensible order. Minor redundancy: the first-call return contents are described twice ('returns confirm_token and...' then 'only returns confirmation_required, a summary, and confirm_token'), costing a sentence.

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 destructive, non-idempotent, token-gated mutation with no output schema and no parameter documentation, the description supplies auth requirements, blocking rules, the two-phase protocol, error behavior, and token lifetime. Nothing an agent needs in order to call this safely is missing.

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 0%, so the description carries the burden. It fully specifies confirm_token (how to obtain it, that it must be echoed with identical arguments, expiry, single-use) and mentions item_id and the optional sheet_number — but never explains what sheet_number semantically controls, leaving one of three parameters opaque.

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 with scope ('Delete one item in this organization') and immediately names the sibling it is not ('For many rows use bulk_delete_items'). An agent can distinguish this from bulk_delete_items and delete_stock_movement without opening a 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?

Explicit routing to an alternative ('For many rows use bulk_delete_items'), a prerequisite ('Requires items.delete'), and a hard precondition that must be resolved elsewhere ('cancel or delete those drafts first'). It even explains which related records do NOT block ('Posted stock movement lines'), which is exactly the exclusion guidance an agent needs.

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