connector_records_get

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

Annotations already declare readOnlyHint=true, and the description adds behavioral context beyond that: it reads the connector_records table that syncs write to, requires no new storage or sync logic, and returns only currently-active records in reverse chronological order. This is useful and consistent with the read-only annotation.

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 first sentence is a clear, front-loaded definition of behavior. The following paragraph is somewhat long but each sentence serves a purpose: differentiating from sibling tools and clarifying that no new storage or sync logic is needed. It is appropriately detailed without filler.

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 read-only tool, the description covers what it returns, ordering, data source, and how it differs from digest tools. However, because schema-level parameter documentation is entirely absent and the description does not define record_type or limit semantics, an agent may still be uncertain how to correctly invoke the tool for a specific record type.

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?

The input schema has no descriptions (0% coverage), and the description does not explain the limit or record_type parameters, their defaults, or accepted values. It only clarifies the connector scope and gives one example involving gmail-sync unread-message records, leaving the agent to guess how filtering and limiting actually behave.

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 opens with a specific action and resource: 'Return one connector's currently-active synced records, most recently observed first.' It also explicitly contrasts this tool with brief_get and agenda_get, positioning it as the only direct accessor of raw connector content, so it is clearly distinguishable from siblings.

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 gives clear context by stating that brief_get/agenda_get provide a folded digest, while this tool exposes raw synced records directly. It doesn't explicitly say 'use this when you need raw records and use brief_get/agenda_get when you need a digest,' but the contrast is strong enough to guide selection.

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