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

Annotations already declare readOnlyHint=true and openWorldHint=true, and the description does not contradict them. The description adds genuine behavioral context beyond the annotations: the subscription/auth requirement ('Requires an active Bidda subscription: pass api_key') and the edge-case semantics of what counts as a delta ('or whose node was withdrawn'). It omits rate limits and response format, but those are secondary for a read-only feed.

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?

Three sentences with zero waste: definition, canonical use case, and operational requirement. The core resource semantics are front-loaded before the usage hint, making the tool's identity clear in the first line.

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?

No output schema exists, so the description carries the burden of conveying what comes back; the first sentence does sketch the output content (source refs mapped to affected obligation nodes). Gaps remain: result ordering, how limit interacts with pagination, and the field structure of a delta item. For a simple read-only feed with fully documented parameters this is nearly 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 coverage is 100%, so the baseline is 3; the description adds value on top by grouping three params into their functional role ('filterable by time, pillar, or specific nodes'). It also flags api_key as effectively required ('Requires an active Bidda subscription: pass api_key') even though the schema declares it optional, which is a useful cross-reference with the header-precedence note.

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?

Names a specific resource ('the obligation-level change feed'), a concrete transformation ('primary sources whose content changed... mapped to the Bidda obligation nodes they affect'), and explicit filter scope ('time, pillar, or specific nodes'). The 'obligation-level' qualifier differentiates it from sibling change feeds like get_latest_changes and watch_changes.

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?

Provides an explicit usage directive: 'Use it to answer "what obligations changed since I last reviewed?"', which clearly frames when this tool is the right choice. However, it never names sibling alternatives (e.g., get_latest_changes or watch_changes) or states when NOT to use it, so contrastive guidance is left to inference.

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