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

Goes well beyond the annotations by disclosing the non-obvious copy-on-write rule: if an order or quote used the address, the edit is persisted as a new address with a new id and the orders/quotes keep the old one, and it tells the agent where to read the new id (result's address.id). It also discloses the auth requirement (signed-in Printdash account, otherwise the connection prompts sign-in on printdash.io) and the validation constraints (AU state codes, four-digit postcodes).

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, front-loaded with the core mutation behavior before the copy-on-write edge case, then the constraints and auth. Dense but every clause carries information; the auth sentence is the only one that could be compressed.

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 needn't be spelled out, yet the description still points at result's address.id where it matters. Auth, validation, and the copy-on-write side effect are all covered; what remains unaddressed is failure behavior (e.g. what an invalid state code or unknown address_id produces).

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 only 45% across 11 parameters, so the description carries weight, and it does contribute the crucial partial-update rule (only supplied fields change) plus the address_id provenance. However, the state/postcode constraints it states are already documented in the schema, and the eight other fields (company_name, mobile, address_line2, type enum, etc.) get no treatment in either place.

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 ('Changes the fields given on one saved address') and immediately pins down the partial-update semantics ('the rest stay'), which distinguishes it from create_address and delete_address in the sibling list. The parenthetical source (list_addresses) also tells the agent where the target id comes from.

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?

Usage is implied rather than stated: the agent can infer this is the tool for editing an existing address versus create_address/delete_address, and the 'from list_addresses' clause supplies a prerequisite. But there is no explicit when-to-use/when-not or named alternative, so the routing decision is left to inference.

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