Christine Friderich – Sophrologue : prise de rendez-vous

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

Annotations already declare readOnlyHint=false, openWorldHint=true, idempotentHint=false and destructiveHint=false, so the write/side-effect profile is known. The description goes further by naming the concrete side effects — calendar entry plus confirmation e-mail — and the 15-minute, free, no-commitment nature, which the annotations cannot convey. It does not discuss failure modes or rate limits, so it stops short of a 5.

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?

Two dense sentences, front-loaded with what happens (call, calendar entry, e-mail) and then the restriction. No filler and every clause carries operational information.

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 5-required-parameter mutation with no output schema, the description completes the picture: who is called, what is created in the calendar, that a confirmation e-mail goes out, and that the slot must originate from voir_creneaux. Nothing essential for correct invocation 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 description coverage is 100% and required fields are documented, so the baseline of 3 applies. The description implies date/heure must come from voir_creneaux and that telephone is the number actually dialed, but adds little format or validation detail beyond 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 un appel découverte de 15 min') with concrete scope — Christine Friderich is the caller, the appointment goes in her calendar, a confirmation e-mail is sent. It is clearly distinguishable from the sibling voir_creneaux, which only lists slots.

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 states the precondition ('À n'utiliser qu'avec l'accord de la personne et ses vraies coordonnées') and routes the agent to the required source of the slot ('sur un créneau renvoyé par voir_creneaux'). This is when-to-use and when-not-to-use in one sentence.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered; the description adds genuine operational context beyond that: the 60-day forward booking horizon, the 14-day default window, day-grouping and a fixed Paris timezone. It stops short of describing pagination or result limits, but adds real value over 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?

The functional payload (free slots, day-grouped, Paris time, 60-day window, 14-day default) is front-loaded and compact. However, a large parenthetical listing the practitioner's location and treated conditions (stress, sommeil, acouphènes, tabac, deuil…) is pure marketing that does not help select or invoke the tool and bloats a single sentence.

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 zero-required-parameter read-only listing tool with a fully documented schema and no output schema, the description covers everything needed to call it correctly: default range, maximum horizon, timezone and grouping. The only gap is that nothing hints at the shape of an individual returned slot, which would have been useful given the absence of an output schema.

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 'du' and 'au' carry their own format documentation), so the baseline is 3. The description goes further by explaining the default when both are omitted ('Sans dates : les 14 prochains jours') and the valid forward range ('de 16 h à 60 jours à l'avance'), which gives the agent boundary knowledge the schema does not encode.

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 clearly that it returns free slots for a 15-minute free discovery call, grouped by day in Paris time, which a caller can distinguish from the sibling reserver_appel_decouverte. The core purpose is present but buried inside a long marketing parenthetical about the practitioner's specialities, which dilutes rather than sharpens the verb+resource.

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?

It gives the effective usage constraints — bookable from 16:00 up to 60 days ahead, and with no dates it returns the next 14 days — which tells the agent how to scope a call. It never explicitly says to consult this before reserver_appel_decouverte, nor states any exclusion, so the when-to-use is implied rather than stated.

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