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

Annotations already declare readOnly/openWorld/idempotent/non-destructive, so the safety profile is covered. The description adds genuine behavioral context beyond that: pagination with a default of 10 items, the 1951–present coverage range with aggregate totals, and the recognition-rate formula (recognized + other_positive = total granted protection), which prevents misinterpretation of results. No contradiction with the annotations exists.

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 and front-loaded: the first sentence carries the core function and data categories, followed by short clauses for semantics, filters, coverage, pagination, and licensing. The license sentence is marginally useful for invocation decisions, and there is slight redundancy with the schema's documented default, but nothing is bloated.

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 low-complexity tool — zero required parameters, all scalars, no enums, full schema coverage, an output schema present, and robust annotations — the description covers the essentials: what data is returned, how to filter, the time range, the page default, and the formula for interpreting granted protection. The only minor gap is that it does not explicitly point to unhcr.asylum.applications as the alternative for application-flow queries, though the category specificity largely compensates.

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% — coa/coo include ISO3 format with examples, year specifies the 1951–present range, and limit documents 1–100 with default 10. The description's filter mention and 'Paginated; default 10 items' largely restate schema content, adding little new parameter meaning. Per the rubric, this is 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 opens with a specific verb-resource pairing ('Get UNHCR asylum decision outcomes') and enumerates the exact data categories returned: recognized refugees, other positive decisions, rejections, and closed/withdrawn cases, by year and country. This specificity unambiguously differentiates the tool from sibling unhcr.asylum.applications, which covers applications rather than decision outcomes.

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 provides clear invocation context: it names the filters (coo, coa, year), states the time coverage (1951–present), and notes aggregate totals, so an agent knows this tool answers decision-outcome queries. However, it does not explicitly name alternatives or state when-not-to-use it (e.g., no explicit 'for applications, use unhcr.asylum.applications'), stopping short of a 5.

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