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

With no annotations, the description carries the load and does add real contract detail beyond the name: exactly one template per kind, whether wording is custom or built-in, the placeholder set per kind, and the locked link placeholder constraint that must remain in the body (valuable context for the save/reset siblings). It does not state side effects, rate limits, or failure modes, but as a read tool the implied safety profile is unambiguous.

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?

A single dense sentence that front-loads the resource and then enumerates kinds and contents; the access restriction is placed last where it acts as a gate. No filler sentences, though the parenthetical enumeration of three kinds is slightly list-heavy for prose.

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 need not be spelled out, and the description covers the key domain constraints (one-per-kind, custom vs built-in, placeholder lock, owner/office permission). The only missing piece is routing guidance relative to the save/preview/reset siblings, which an agent would otherwise have to infer from names alone.

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 description coverage is 0% and the description never mentions shop_id, so nothing is added beyond the schema's uuid-typed required field. The gap is mitigated by there being only one, self-evident scoping parameter, so an agent will not mis-map it — but no compensation for the coverage hole exists.

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 concrete resource (the shop's customer message templates) and enumerates the template kinds (invoice_reminder, quote_followup, review_request) plus what each entry contains (wording, placeholders, locked link placeholder). It reads clearly as a read/list tool, though it never names the siblings it must be distinguished from (messages_saveTemplate, messages_previewTemplate, messages_resetTemplate).

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 implies the operational context — inspect current wording and placeholders — but never says explicitly when to call this versus messages_previewTemplate, messages_saveTemplate, or messages_resetTemplate. The 'Owner or office only' clause is the only concrete usage condition given.

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