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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, covering the safety profile. The description adds useful behavioral context beyond annotations: it returns an array of connection records, supports multiple filter dimensions, and supports pagination, which helps an agent anticipate response shape and usage.

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 with no filler: action and scope first, return shape second, filtering and usage guidance third. Every sentence earns its place, and the critical sibling distinction is included without bloating the description.

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?

The description covers the core operation, return shape, supported filters, pagination, and the relevant single-record alternative. With zero required parameters and no output schema, this is largely sufficient for an agent to invoke it correctly. Slight gaps remain around the meaning of env and exact pagination mechanics, but these are minor relative to the tool's straightforward list semantics.

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 63%, so the schema already documents most parameters. The description enumerates several filterable parameters (updated_gte, sort, order, external_xref, categories, env, pagination) but adds little semantic depth beyond repeating their names; notably, env and sort still lack meaningful explanation. The pagination umbrella term slightly compensates, but meaning is not substantially expanded.

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 verb and resource, 'List connections from the connected account,' which clearly identifies the operation and its scope. It also differentiates itself from the sibling get_unified_connection by explicitly framing this as listing many connections versus fetching a single one by ID.

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?

Explicitly states when to use this tool ('to browse or search many connections') and names the exact alternative for the single-record case ('to fetch a single connection by its ID, use get_unified_connection'). This leaves no ambiguity about which sibling to choose.

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