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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds two useful facts beyond that: the underlying endpoint (GET /v1/integrations/{type}) and that the call is 'Free', which signals no credit consumption. It does not mention response shape details, error behavior for unknown types, or whether the full settings payload is always returned.

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 sentence plus a parenthetical endpoint reference; the scope-defining phrase comes first and nothing is wasted. The 'Free.' cost note is terse and high-value.

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 one-parameter read-only tool with full schema coverage, complete annotations and no output schema, the description tells the agent what entity is fetched and that connections plus settings are included. It could say slightly more about what happens for an unconfigured type, but nothing essential to correct invocation is missing.

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 100% and the single 'type' parameter carries a documented enum of 42 ESP slugs with examples (klaviyo, mailchimp, brevo). The description adds nothing about the parameter beyond echoing {type} in the path, so the baseline 3 applies.

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 names a specific resource (one integration type) and states its scope precisely: the integration plus all of its connections and their settings. It implicitly contrasts with the plural 'list_integrations' by emphasizing 'One integration type', but never names a sibling explicitly, so an agent must infer the boundary with list_integrations and get_connection.

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 only implied: 'One integration type with all of its connections' suggests fetching a single ESP's detail view rather than enumerating all integrations, but there is no explicit when-to-use, no when-not-to-use, and no named alternative such as get_connection for a single connection.

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