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

Goes well past the annotations: states secrets and OAuth tokens are never returned, that results are one page, and gives explicit pagination handling instructions ('say so rather than presenting the page as the whole set'). Annotations already cover read-only/idempotent/non-destructive, so this adds genuinely new behavioral context.

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?

Front-loaded with the core purpose and safety note, and each sentence is substantive. It is slightly long, using two sentences to make the single pagination point, but nothing is 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?

With an output schema present, return-value detail is not required, and the description covers the safety, scope, and pagination behavior an agent needs. The remaining gap is parameter guidance for the under-documented schema, which keeps it short of complete.

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 only 25% (only workspaceId is documented), so the description should carry more weight. It gestures at 'optional bounded provider resources' but never explains limit, providers, or the resources/include structure, and doesn't clarify the workspaceId scoping rules that matter in multi-workspace accounts.

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 (Read) and resource (connected integrations) plus the optional extra surface (bounded provider resources and import progress). It also explicitly fences off what it is not (connect, disconnect, send leads), which separates it from siblings like connect_account and configure_integration without naming them.

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?

Gives a concrete trigger ('Use this before provider export/import calls') and three exclusions, which is more than most definitions offer. It stops short of naming a specific sibling or the alternative to use when the intent is actually to connect/import, so it is clear context rather than full routing.

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