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

Annotations already declare readOnly/openWorld/idempotent, and the description adds meaningful non-redundant context: the data source (Google COVID-19 Open Data), that no auth is required, and that the data is historical and frozen since 2022-09-15. It also previews the output's key field and its role in downstream calls, which helps the agent understand behavior beyond safety traits.

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?

Four tightly written sentences, each carrying distinct information: action, output/downstream use, data source/auth, and temporal status. Purpose is front-loaded, and no sentence is redundant with the schema or annotations.

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?

The description covers the tool's role, parameter classes, return key, downstream usage, data source, authentication, and data freshness. An output schema exists, so detailed return structure needn't be repeated; nothing essential to selection or invocation 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?

The input schema contains full descriptions for all three parameters (100% coverage), so the baseline of 3 applies. The description merely paraphrases the schema's filter dimensions ('free-text name, ISO country code, and/or administrative aggregation level') without adding new semantic detail beyond what the schema already provides.

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 pair ('Search/list COVID-19 tracked locations') and names the three filter dimensions. It also positions itself as the key-lookup step for the sibling tools by stating 'use the returned location_key with global-health-covid.latest_snapshot or global-health-covid.location_history,' which distinguishes its role from those siblings.

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 provides clear guidance by naming the two sibling tools that consume its returned location_key, effectively telling the agent when this tool is the necessary precursor. It lacks an explicit 'when not to use' statement (e.g., if you already have a location_key, go directly to the snapshot/history tools), but the downstream pointer is a strong and specific usage hint.

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