link_account

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

With destructiveHint=true and idempotentHint=true already declared, the description still earns credit: it discloses that prior values are replaced (the actual destructive act), that the handle is validated for existence first (implying possible failure), and that stats are returned. It does not say what error surfaces when the handle doesn't exist or what happens if the platform is unknown.

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 short sentences, front-loaded with the action and its replacement semantics. The middle clause ('after checking it exists') is awkwardly placed after the replacement clause, creating a slight order-of-operations ambiguity, but nothing is padded.

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?

An output schema exists and the description only briefly notes stats are returned, which is sufficient on that front. But for a destructive, open-world mutation whose parameters are entirely undocumented in the schema, the definition leaves the platform input space and failure behavior under-specified.

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 the meaning of 'platform' and 'handle' — and it only gestures at them via 'username on a platform' and 'handle.' It gives no format, casing, or accepted-value guidance for platform despite a list_platforms sibling existing, and never clarifies whether 'username' and 'handle' are the same field.

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: 'Save the user's username on a platform,' and adds the upsert semantics ('replacing any saved before'). The downstream effects (handle defaults, show_dashboard stats) make the resource's role unambiguous, though it never names unlink_account as the inverse operation.

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?

Usage is only implied — an agent can infer you call this when a user wants their platform account remembered. The forward references to 'tools that take a handle' and 'show_dashboard' describe consequences, not when-to-use-vs-alternative decision rules, and there is no when-not guidance (e.g., calling twice safely, or how it relates to unlink_account).

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