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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and openWorld, so the safety profile is covered. The description adds genuinely non-redundant behavior: pricing is per listed service, fees and the final total are confirmed only on the website, results reuse DriveLab location coverage and ordering, and it explicitly does not book. It omits any return-shape or pagination notes, but the extra context is substantial.

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?

Four short sentences, front-loaded with the purpose, then the pricing caveat, then the routing handoff, then the scope limit. Almost every sentence earns its place. The one soft spot is 'Reuses DriveLab location coverage and ordering,' which is internal jargon of limited use to an agent.

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 still tells the agent what identifiers come back (instructor_id, service_id) and that prices are per service, which is the minimum needed to chain into get_lesson_availability. It does not describe result ordering in user-facing terms or result volume, leaving a small 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 75%, which is near the threshold where the schema carries the load: city, language, and teaching_language are documented in the schema. The description only echoes the town concept and adds no syntax or semantics for category (which has no schema description at all) or for the language-vs-teaching_language distinction. Baseline 3 is appropriate.

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 names a specific verb plus two concrete resources — 'published driving-school profiles' and 'bookable individual services' — for a bounded geography (a Swiss town). It separates itself from get_lesson_availability by reserving slot lookup for that sibling. It does not, however, explicitly distinguish itself from search_courses or list_course_locations, so an agent must infer the boundary.

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 a positive routing instruction: 'Use get_lesson_availability with returned instructor_id and service_id for free slots,' and a clear exclusion: 'Does not book.' That covers the most likely next step. It stops short of contrasting against the other siblings (search_courses, list_course_locations), which limits it below a 5.

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