Rechercher des notifications

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the safety profile is covered. The description adds the important API constraint about category being required (even though schema also marks it required), and clarifies parentType as array of module types. It doesn't describe pagination/return details, but with read-only annotations the bar is lower and the description adds meaningful context.

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 description is compact, front-loaded with a clear purpose statement and a warning about the required category parameter. It uses formatted Args blocks that are scannable. The redundant Args section partially repeats schema info but is useful for quick reference. Slight redundancy between the warning note and the Args list, but overall efficient.

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 search/filter tool with read-only annotations, strong schema coverage (100%), and no output schema, the description conveys the core query capabilities adequately: category (required), state, parentType filters, as well as pagination and field projection hints. It lacks explicit statement about empty-result behavior or sorting, which are minor. Given the schema carries the bulk of parameter documentation, this is reasonably complete.

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%, so the schema already documents all 6 parameters thoroughly. The description adds value by explicitly noting category is required (though redundant with schema required), and by giving examples for parentType ('contract', 'global') and the fields projection ('title','updateDate'). However, this mostly restates what the schema already provides, so it doesn't substantially exceed the baseline 3.

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 states 'Recherche des notifications dans BoondManager' — a clear verb (rechercher) + resource (notifications). It also adds a critical API requirement ('category' is REQUIRED by the API, singular, not array), which is valuable specific detail. It distinguishes from sibling boond_notifications_get by being a search/list operation.

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?

The description explicitly clarifies the required category parameter and its valid enum values. It lists the other optional filters and their purpose. It doesn't explicitly name alternative sibling tools or state when-not-to-use, but the search-vs-get distinction is implied by the tool naming pattern and the search semantics are made clear. A small gap remains on when to prefer this over other search tools.

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