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

Annotations already declare non-read-only, non-idempotent, non-destructive, so the write profile is known. The description still adds substantial behavior: the hold window (30 minutes, never later than 15 minutes before), that the pay link is single-use, that ElloMind sets the price and the agent cannot, that the psychologist may be refused with 'not free', that all validation problems return at once, and concrete rate limits (3 unpaid drafts per phone, 8 drafts per hour per network). These are real value-adds beyond the annotations.

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 the core action and the check_availability dependency, and every sentence carries operational content. It is delivered as one dense wall of text with nested asides (a reference to a 'by_psychologist' field that is not in this schema), which makes the branch conditions harder to scan than they need to be.

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 17-parameter, 9-required, nested-object mutation with no output schema, the description covers what comes back (psychologist slug, name, role; the pay link), the failure modes ('not free', batched validation errors), the temporal constraints, and the quota limits. An agent has enough to call it correctly and interpret the result.

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 88%, so the baseline is 3, and the description goes beyond it by explaining conditional semantics the schema only hints at: psychologist is the slug and, when omitted, ElloMind assigns anyone free but the response names who was assigned; lead_source defaults to ai_assistant if the customer did not say; booked_by is 'customer' for self-booking; partner_2 needs each partner's own contact and consent; teen contact must be the parent/guardian. It leaves source_ref, lead_detail, email_checked and teen_age entirely to the schema, so not a 5.

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 with scope: hold one time slot with one psychologist and return a single-use pay link. It distinguishes itself from check_availability (which supplies the time) and from cancel_booking_draft (which frees a draft), so an agent can route correctly without opening a sibling schema.

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?

Explicit prerequisites ('Call check_availability first and use one of its times'), explicit conditional branches for psychologist / no psychologist, couples, and teen, plus a hard cutoff ('Bookings close 10 minutes before the session') and a named fallback tool (cancel_booking_draft frees a draft). Alternatives and when-not conditions are stated, not implied.

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