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

Annotations already establish readOnly/non-destructive/closed-world, but the description adds genuinely non-obvious behavior: visibility rules (assistant-only teams are excluded), the scope taxonomy (self/team/nolio), the is_nolio read-only flag, and the fallback-with-hint matching mode. This is exactly the kind of context annotations cannot convey.

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-loads the corpus scope before result shape and edge-case handling, and every clause carries information. It is a dense single paragraph with heavy parentheticals, which makes it slightly harder to scan than a segmented form would 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?

There is no output schema, and the description compensates by enumerating the returned fields (id, name, type, is_load, laterality, scope, is_nolio) and explaining the laterality enum inline. Combined with the fallback and not-found guidance, an agent has everything needed to call this correctly and interpret the results.

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% and already documents query (name/fragment, FR or EN), type enum, and is_load, so baseline is 3. The description adds real value on top by framing query as a name-based disambiguation step with word-level fallback semantics, which the schema does not state.

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 (search exercises by name) and precisely delimits the corpus: own exercises, visible team libraries (explicitly excluding teams where the user is only an assistant), and the shared Nolio global library. That scope language also differentiates it from siblings like list_library_categories or get_training, which deal with adjacent but different resources.

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?

Gives explicit when-to-use and when-not rules: the search is 'the disambiguation step, never guess an id', and if nothing is found the agent must tell the user and propose creation rather than invent an exercise. It also documents the word-level fallback path so the agent knows what a miss actually means before acting.

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