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

Beyond the annotations (readOnly/idempotent/non-destructive), the description discloses two traits annotations cannot express: it is free, and it never raises a protocol error but instead returns {"error": "<what is wrong and how to fix it>"} with a concrete example. That error contract plus the retry-safety note is exactly the kind of behavioral context an agent needs and structured fields do not carry.

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-loaded with the purpose and the free/read-only guarantee, then example, then usage, then error contract. It is dense and nearly every clause earns its place, but the inline multi-line JSON blobs make it visually heavier than necessary and slightly slow to scan.

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 3-parameter, typed, single-object tool with an output schema, the description covers purpose, argument edge cases, sibling routing, cost, error semantics and retry safety. Nothing an agent needs in order to call it correctly is missing; return shape is even illustrated despite the output schema already documenting it.

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 would be 3, but the description adds value the schema lacks: a worked input example ({regime, event_type, obligation}) paired with the shape of the response, which clarifies how the three arguments compose. It stops short of enumerating valid regime/event_type/obligation values, deferring to list_regimes.

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: 'Quote the time limit, citation and required content for an obligation.' It also draws the boundary against the sibling that shares the same domain ('Not for computing dates: use compute_deadlines'), so an agent can discriminate it from the deadline-computation tools without opening a schema.

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 an explicit inclusion criterion ('when a caller needs the rule's own words next to a computed date'), an explicit exclusion with a named alternative (compute_deadlines), and edge-case guidance for empty arguments ('leave obligation empty to get every obligation…; leave event_type empty on single-event regimes').

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