invite_circle_member

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

Annotations only say readOnlyHint=false and destructiveHint=false. The description goes well beyond by disclosing that the invite is single-use, that it returns Telegram/WhatsApp deep links and a QR code, and that the member binds their messenger identity by tapping the channel-matched link. The auth prerequisite is a genuinely useful operational detail. It does not cover invite expiry, re-invocation behavior, or whether an unused invite can be revoked.

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 what the tool produces and what the caller gets back, then a separate ACCESS block for the prerequisite. Every sentence earns its place; no restating of the name or schema.

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?

No output schema, yet the description compensates by naming the return payload (deep links + QR code). Inputs are simple and fully documented. Lifecycle details (invite expiry, whether a new invite supersedes an old one, error cases) are the only notable gap.

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 100% with two 24-hex-char ID parameters fully documented ('Circle ID', 'Member ID to invite'), so the schema carries the parameter burden. The description adds no format, constraint, or relationship detail about id/member_id beyond what the schema already provides.

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 resource ('Mint a single-use enrollment invite for a Circle member') and immediately clarifies the mechanism: channel-matched deep links plus QR code. An agent can distinguish this from the nearby add_circle_member / add_circle_member_channel siblings, which do not involve an invite artifact.

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 a concrete precondition (needs a Proof account; set PROOF_API_KEY and restart the server) and an explicit negative: 'start_login does NOT open this tool,' which prevents a plausible wrong path. It stops short of saying when to choose an invite over directly adding a member/channel, so an alternative-selection rule is still missing.

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