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

Beyond annotations (readOnlyHint=false, idempotentHint=false, destructiveHint=false), the description discloses critical behavioral traits: the consent gating mechanism, the fact that hostel bookings are HOLDs needing payment, the silent failure of tg:// links, and that identity comes from Telegram consent rather than collected fields. This is a wealth of behavior not inferable from annotations alone.

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?

While lengthy, the description is front-loaded with an action statement, then uses labeled sections (Doctor:, Hostel:, Spa:, CONSENT:) to organize dense but necessary information. Every sentence adds critical operational detail, so the length is justified.

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 must explain return values, and it does: consent_url/telegram.consent_url, consent_url_native, payment_url, and the immediate-success case. It also covers edge cases (silent tg:// failure, already-authorized retry), making it complete for a complex booking tool.

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?

The schema lists only provider_id and item, with 50% description coverage (provider_id undocummented). The description compensates by explaining provider_id + item semantics, detailing item structures per venue type (doctor, hostel, spa), and explicitly warning not to ask for name/contact. This fully bridges the gap left by 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 description states the tool's primary action clearly: 'REAL action: book at a network venue on the user's behalf.' It distinguishes from siblings like cancel, reschedule, and find_providers by being the actual booking action. It also specifies different item structures for doctor, hostel, and spa, leaving no ambiguity about what the tool does.

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 provides an explicit workflow: call book directly, handle consent flow if consent_url is returned, retry after consent, and for hostels, note that booking returns a HOLD finalized by payment. It also explains when NOT to prompt for consent (if already authorized) and how to handle consent_url_native. This is superior guidance beyond simple 'use for booking'.

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