Connect a paste-a-key account

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

Annotations already declare readOnly=false, destructive=true, openWorld=true, idempotent=true, but the description adds substantial behavior beyond them: live key validation with the provider before anything is saved, read-back of the reply from the saved connection, the guarantee that Hermoso never echoes a submitted key, the credential-exposure tradeoff of pasting into chat vs. the app, and the special Apple Ads keypair/setupToken flow. These are real operational facts an agent needs and they are not derivable from the annotations.

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?

Purpose and provider list are front-loaded and almost every sentence carries operational weight, so there is little padding. The weakness is formatting: a single ~250-word paragraph buries the agent directive ('OFFER BOTH WAYS...') and the field inventory mid-block, which hurts scannability, but the content itself earns its place given the tool's complexity.

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 no output schema, the description still covers outcomes (live check, saved-connection read-back, OAuth fallback link, Apple Ads keypair plus setupToken send-back) and the security expectations. For a 2-parameter but highly variant, open-world mutation tool with nested free-form fields, an agent has everything needed to call it correctly.

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 already 100%, but the schema only offers a free-form 'fields' object; the description supplies the actual per-provider field names and marks required ones with '*' (e.g. mixpanel {username*, secret*, projectId*, region, workspaceId}), which is the only place that contract exists. This adds decisive meaning well beyond 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?

The first sentence gives a specific verb (connect), a precise resource (an account that links with a KEY rather than a sign-in screen), and the modality (from here, no browser) that separates it from OAuth flows. It also enumerates the exact providers supported, so an agent knows immediately whether this tool applies to the user's request.

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?

Explicit when-not routing is present: 'An account that connects through the provider's own sign-in screen (OAuth) cannot be connected here: this answers with the link to hand the user instead.' It also gives an explicit agent instruction ('OFFER BOTH WAYS AND LET THE USER CHOOSE') and the alternative path (Workspace > Connectors or the one-click link). Nothing about selection is left to inference.

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