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

Annotations already mark the tool as readOnly and idempotent, and the description goes beyond that by disclosing that items are metadata-only and that each carries a locator usable by get_provision. It also explains the default kind behavior, adding useful context that annotations do not capture.

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 concise sentences with no filler: the first identifies the resource and metadata nature, the second states defaults and the recital override. Every clause earns its place and the purpose is front-loaded.

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?

The output schema covers return values and annotations cover safety, so the description need not restate those. However, with six parameters and no schema-level descriptions, the semantics of limit, cursor, topic, and chapter are left to inference, making the definition incomplete for correct invocation.

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 schema description coverage at 0%, the description must compensate, but it only explains kind and indirectly instrument_id. Parameters limit, topic, cursor, and chapter receive no semantic guidance, leaving most of the six-parameter surface underspecified.

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 opens with a clear question identifying the resource: provisions contained in an instrument. It specifies 'Metadata only' and connects to get_provision by noting each item carries the exact locator that tool accepts, which differentiates it from its sibling.

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 gives clear selection context by stating that articles and annexes are returned by default and that kind=recital switches to recitals. It implies that full provision content belongs to get_provision, but it does not explicitly list when-not conditions or compare against search-related siblings.

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