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

Annotations already cover the read-only, idempotent, non-destructive, non-open-world profile, and the description adds real value beyond them: it discloses that the caller needs connections:write, that this service lacks the credentials to complete consent/confirmation/revocation, and that the response carries an explanatory sentence. The apparent tension between readOnlyHint=true and a write scope is disclosed rather than contradicted, which is exactly the context an agent needs.

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?

The length is reasonable and there is little filler, but the opening is a relative clause ('Where the merchant connects...') instead of the front-loaded statement an agent needs — 'Returns a dashboard link for...'. The key fact, that this returns a link rather than performing anything, arrives late and only implicitly.

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 two-parameter, read-only tool with no output schema, the description covers the security scope, the hard capability limit (no credentials for consent/revocation), and hints at the return payload ('plus a sentence saying what happens there'). What is missing is a concrete statement of the returned link's form and per-action expectations, but the critical call-safety facts are present.

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 0%, so the description must carry parameter meaning, and it only partly does. It enumerates the action values in prose (connect, reconnect, map_locations, disconnect) and implies that consent/location confirmation/revocation map to specific action branches, but the provider parameter and the returned-link semantics for each action are never explained; the enums do much of the remaining work.

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 description identifies the domain (connecting/reconnecting/mapping/disconnecting a POS or catalog source) and explicitly states it does not perform the action, but it never plainly says it returns a link/URL to a dashboard page. An agent must infer the return from the tool name and the oblique phrase 'Where the merchant connects...' rather than from a stated verb+resource.

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?

It clearly carves out what the tool is not for — consent, location confirmation and revocation happen in the dashboard, not through this service — which tells the agent when not to expect completion. However, it gives no explicit routing versus siblings such as list_connections or get_billing_link, so the choice among related tools 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.