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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so safety needs no restating. The description adds genuinely useful interpretive context the annotations cannot: each figure carries legal basis, source tier and date, and 'absence means UNVERIFIED, never that no route exists' prevents a serious misreading of empty results. It stops short of describing result ordering or how the three modes interact if multiple parameters are supplied.

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 topic and the three modes numbered, so an agent can stop reading once it matches a mode. It is dense and long for a description, with a slightly redundant closing line ('Information, not legal advice'), but nearly every clause carries operational content.

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?

With 9 optional parameters, three operating modes and an output schema already present, this covers what an agent needs to choose a mode and populate its parameters, plus the critical unverified-absence caveat. The remaining gap is mode precedence when parameters from different modes are combined, which matters given that all nine parameters are optional.

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 earns an extra point by binding each parameter to its mode and adding semantics beyond the schema, notably that together_required means no later add-on and that children_ages should be completed years as an array. Mode-to-parameter mapping (parents, partner, together_required all 'screen mode') is spelled out, though the interplay of simultaneously supplied programme_id and cc is not resolved.

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 names a specific domain (family dependants and reunification) and enumerates exactly what it answers: which relatives qualify, age limits and how age is measured, same-time vs later joining, aging-out, and per-category costs. It also distinguishes itself from the broader pathway tools by scoping strictly to the family/dependant slice of a programme, so an agent can separate it from find_pathways, get_programme or compare_programmes 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?

It gives explicit mode selection guidance with concrete trigger examples: programme_id for one programme's dependant record, cc for a country's reunification law by sponsor class, and screen with children_ages for ranking whole-family options. What is missing is an explicit negative: nothing says when NOT to use this (e.g. for the main applicant's own eligibility) or which sibling to fall back on.

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