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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context: pagination with default 10 items, and the open data license with no cost. It also enumerates the specific metric categories returned (refugee counts, asylum seekers, IDPs, etc.), which goes beyond the annotations. No contradictions with annotations.

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 a single, well-structured paragraph. It front-loads the core purpose, then details the metrics, filters, pagination, and licensing in a logical order. Every sentence carries information: no fluff or redundancy. It is appropriately sized for the tool's complexity, avoiding verbosity while covering all essentials.

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 that an output schema exists, the description doesn't need to detail return values. It covers all input parameters, filter semantics, pagination defaults, and data licensing. It could mention how to request subsequent pages (e.g., a page parameter or offset), but that is a minor gap. For a read-only, open-data tool with no authentication or rate limits disclosed, 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 all four parameters are described in the input schema. The description enhances this by providing concrete examples for each filter (e.g., SYR, AFG, UKR for origin; DEU, TUR, COL for asylum) and clarifies that omitting filters yields global aggregates. This adds practical meaning beyond the schema's generic descriptions, though the schema already does heavy lifting.

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 clearly states the tool's function: retrieving UNHCR refugee and displacement statistics by country or globally. It specifies the exact resource (population statistics), the time range (1951–present), and the metric types returned. This distinguishes it from sibling tools like unhcr.asylum.applications and unhcr.asylum.decisions, which focus on asylum procedures rather than population counts. The verb 'Get' is specific and actionable.

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 usage context: it explains how to filter by year, country of origin, and country of asylum, and explicitly states that omitting all filters returns global aggregates. It also mentions pagination and default limit. However, it does not explicitly mention when not to use this tool or compare it to alternatives like unhcr.population.solutions or unhcr.asylum.*, though the distinct scope makes it inferable. The guidance on filter omission is particularly helpful.

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