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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds meaningful behavioral context beyond that: 'Paginated; default 10 items' and 'Covers 1951–present with totals when available,' plus the list of data dimensions included in responses. No rate-limit or auth details, but for a read-only open-data tool these are not critical gaps.

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: it opens with the core purpose, then layers dimensions, filters, time coverage, pagination, and licensing in three information-dense sentences. The license note is a minor extra but not pure filler. It earns its length.

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?

Given an output schema exists, the description doesn't need to explain return values. It covers the data granularity, all filter options, time range (1951–present), pagination behavior, and licensing. There is nothing an agent needs in order to select and invoke this tool correctly that is missing.

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% — each of the four parameters has a description with examples and omission semantics. The description echoes the filters ('Filter by year, country of origin ISO3 (coo), or country of asylum ISO3 (coa)') and pagination default, but adds no new meaning beyond what the schema already provides. Thus the baseline 3 is appropriate.

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 and resource: 'Get UNHCR asylum application counts — number of new asylum claims filed by year and country.' It clearly distinguishes from sibling tools like unhcr.asylum.decisions by focusing on applications/claims filed rather than decisions, and it enumerates the data dimensions (procedure type, application type, decision level, applicant category) that define the output scope.

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?

Clear context is provided: this tool returns asylum application counts filterable by year, coo, or coa. However, it never explicitly names alternatives (e.g., unhcr.asylum.decisions) or states when not to use it; the differentiation is implied by the 'applications' vs. 'decisions' wording rather than stated as an exclusion.

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