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

Goes beyond the annotations (readOnlyHint=false, destructiveHint=false) by disclosing that the change 'reaches no one', is reversible via another update, and therefore runs without confirmation. It also names the auth requirement (Cotlet API key). This is meaningful behavioral context the annotations alone do not convey.

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-loads the core action in the first sentence and stays reasonably tight. The rationale clause ('so it runs without asking') is slightly chatty but earns its place by justifying no-confirmation behavior.

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 mutation tool with no output schema, it covers reversibility, auth, and the state-transition rule, which is what an agent needs to call it correctly. Return/confirmation format is left implicit, which is acceptable given no output schema exists.

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 100%, so the baseline is 3, but the description adds real meaning by explaining that Category, Supplier, and Total amount are the fields whose presence triggers the item to move to Ready — a parameter-to-workflow interaction not expressed in 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?

States a specific verb-plus-resource ('Change extracted fields of an item') and gives concrete field examples (supplier, category, date, total). It is clearly distinguishable from read siblings like dext_get_item and dext_list_items, though it never names an alternative explicitly.

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?

It explains the partial-update semantics ('Updates the fields you pass and leaves the rest') and the Ready transition, which implies when to reach for it. However, it never routes the agent against alternatives (publish_items, archive_items, get_item), so usage must be inferred from context.

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