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

Annotations already declare destructiveHint=true and openWorldHint=true, so the description earns credit for adding genuinely new behavioral context: credentials are validated against the real provider before saving, failures return the specific reason, and credentials must never be echoed back. These details go well beyond the structured fields.

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, front-loaded with the primary action and instructions, with no filler. The parenthetical slightly interrupts flow but every clause carries actionable content.

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 destructive, open-world write tool with no output schema, it covers validation, failure handling, field sourcing, and credential privacy. It omits what happens on success or whether an existing connection is overwritten, but remaining gaps are minor.

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 coverage is 100%, so both params are already documented (baseline 3). The description adds real meaning by specifying that field names must come from integration_guide, clarifying the nested 'fields' object's expected keys beyond the schema text.

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+resource ('Connect one of the user's accounts') and clarifies the mechanism (values pasted in chat). It distinguishes itself from the external-website path and routes to the sibling integration_guide for field names, so an agent can identify it without inspecting the schema.

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 the supported usage ('values they pasted in this chat'), the exclusion ('do not send the user to a website instead'), and the prerequisite/discovery source ('Field names come from integration_guide'). This is the when/when-not/alternative guidance an agent needs.

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