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

Goes meaningfully beyond the annotations by disclosing the 6-hour sync cadence and, importantly, that credentials are validated with one read, sealed, and never returned — a real trust and security fact an agent cannot infer. It does not address the destructiveHint=true implications (e.g., whether reconnecting an existing provider duplicates contacts or overwrites the list), which is the main gap for a mutation tool.

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 effect and cadence, then the provider list, then consent/phone semantics, then credential handling — a logical order. The parenthetical provider credentials make the single paragraph dense but every clause carries information; slight tightening could improve scanability.

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 21-parameter, non-idempotent, destructive, open-world tool with no output schema, the description covers the essentials: what gets created, the sync cadence, consent and phone sourcing, and credential safety. Missing pieces are the failure/re-connect behavior and what the created list looks like, which matter for a destructive operation.

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?

With 90% schema coverage the baseline is 3, but the description adds genuine cross-parameter structure the flat schema cannot express: which credentials belong to Mixpanel (projectId, username, secret as service account) versus Amplitude (apiKey, secretKey) versus HubSpot (accessToken), and how consentEvent/consentField and phoneField interact with consent and phone capture. The per-provider mapping is the key value-add over the schema.

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?

Names a specific verb and resource ('connect a tool') and adds the concrete effect: people sync in as contacts, into a dedicated list, every 6 hours. It enumerates the supported providers and the credential shape per provider, which makes the tool unmistakable. It does not explicitly distinguish itself from near-siblings such as update_integration, sync_integration, or disconnect_integration, so it stops short of a 5.

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 when to use it (setting up a new provider connection) and the mode parameter explains pull vs. push behavior, which is helpful context. However, there is no explicit 'use this instead of X' routing to update_integration, sync_integration, or list_integrations, and no stated preconditions for an already-connected provider.

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