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

Annotations already flag this as non-readOnly, destructive and open-world, so the safety profile is pre-declared. The description goes beyond that with concrete behavior: single-use state, 10-minute expiry, credential lands in the company vault via provider callback rather than the conversation, a 409 target_required path, and a landsOn field in the reply. That is substantive added 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 action and return shape before the edge-case routing rules, so the important part lands first. It is dense and em-dash-packed, and a clause or two (e.g. the provider sign-in caveat) could be trimmed, but nearly every sentence carries operational information.

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 9-parameter mutation with no output schema, the description supplies the return shape ({url, expiresAt}), the lifetime and single-use constraint, the 409 failure mode, and who must be authenticated (the human, at the provider, not here). Nothing an agent needs to call this correctly 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 coverage is 100%, so baseline is 3, but the description adds real semantics on top: the precedence and purpose of reconnectId vs instanceName, the exact condition that justifies newConnection, and the error payload shape listing instanceName, reconnectId and accountName. Minor parameters (person, install, directory, environment) are left to the schema, which already documents them.

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 and artifact: 'Mint the provider's authorize URL for an OAuth connector,' and names concrete services (google_cloud, microsoft, cloudflare, discord, github). This is clearly distinguishable from siblings like connections_apps or connections_explore_connectors, which inspect rather than mint links.

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 explicit routing rules: pass reconnectId or instanceName to re-consent an exact row, pass newConnection:true only to add another account, and expect a 409 target_required when live connections exist and neither is supplied. It also explains why re-consent is needed (a scope added to a connector never widens an existing grant), which is genuine when-and-why guidance.

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