Citable — connect a sign-in wallet (no crypto needed)

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

Annotations (readOnlyHint=false, openWorldHint=true) already signal mutation and real-world effects, and the description adds substantial context beyond that: the 15-minute link expiry, the significant disk side effect ('installs Para's SDK under ~/.config/citable/para (about 200 MB, once)'), and the state transition semantics of reset (disconnects and returns to keypair) versus status (only reports, no new connection). This is exactly the behavioral context an agent needs before invoking a tool with world effects.

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?

Five dense sentences, each carrying distinct information: audience/pricing, the connection flow, the timeout and follow-up sibling, the flag semantics, and the install side effect. The most decision-relevant facts (free, non-crypto audience, returns a link) are front-loaded. No filler or repetition of schema 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?

With no output schema, the description correctly explains the return value ('Returns a link to open in a browser'). For a complex tool involving browser interaction, a persistent 200 MB install, a 15-minute expiration, and two mode flags, the description covers the full lifecycle: initiation, confirmation via citable_prices, status reporting, and reset. Nothing an agent needs to call it 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% — both boolean parameters already have clear descriptions in the schema ('Forget the sign-in session and pay from the keypair again', 'Only report the current state; do not start a new connection'). The description lightly restates this ({status:true} only reports; {reset:true} disconnects) within the flow narrative, adding marginal value, so the baseline 3 is appropriate.

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 states a specific verb and resource — 'connect a sign-in wallet' — and fully explains the mechanism (returns a browser link, sign in with Google/email, add USDC, click Connect). It clearly differentiates from all sibling tools, which are keyword/SEO research tools; citable_connect is uniquely about wallet connection and payment. The flow is concrete enough that an agent knows exactly what this tool accomplishes.

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?

The description gives an explicit alternative: 'when the user says it is done, call citable_prices to confirm (walletMode becomes sign-in)', telling the agent exactly when to switch to a named sibling. It also frames the audience condition ('For people who do not use crypto') and explains the status/reset flags as distinct modes. The when-not case (default keypair path) is only implied via 'returns to the keypair', not explicitly stated, which keeps this short of a 5.

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