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

Goes well beyond the annotations (destructiveHint, openWorldHint) by disclosing the pre-flight re-check ('revérifié libre juste avant'), the refusal when the slot is held for another contact, the success side effects (appointment created, held slots released, card set to « RDV pris » with date), and that no message is sent. This is exactly the kind of mutation impact an agent needs before calling.

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 verb and resource, then preconditions, refusal behavior and success effects; every sentence carries operational information. It is dense (four clauses separated by semicolons) but not padded, though the provider requirement list could be tightened.

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 no-output-schema, destructive write tool this covers the full picture: prerequisites per provider, failure/refusal conditions, the re-verification step, and the post-success state change including the freed holds. Nothing an agent needs to invoke it safely 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?

With 100% schema coverage the baseline is 3, but the description adds non-schema meaning: email is mandatory for GoHighLevel and Calendly yet optional for Google Calendar, which tells the agent when a missing email will cause refusal. lead_id and start semantics are left entirely to 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?

States a specific verb and resource ('Réserve dans l'agenda connecté le créneau') plus the exact scope: a slot the contact ACCEPTED, drawn from ficiel_get_slots. An agent can distinguish this from ficiel_get_slots (which only lists slots) and from messaging tools without opening any 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?

Explicitly names the upstream source (ficiel_get_slots) and the precondition that the slot be accepted, and lists per-provider prerequisites (GoHighLevel email/phone, Google none, Calendly email + paid plan) with a refusal path when unmet. It does not differentiate from the sibling ficiel_mark_booked, which is the closest alternative for recording a booking, so it falls short of a full when/when-not comparison.

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