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

The annotations already mark the tool as read-only and idempotent, and the description adds valuable behavioral context beyond that: it explains that every figure except the count is a percentage of the unit's urban dwellings, that vacant dwellings are included even though they appear in no census household record, and that units without urban areas return nothing. No contradiction with 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 long but every sentence carries essential information: the first sentence front-loads the full scope and metric list, the second clarifies percentage semantics, the third removes ambiguity about dwellings versus households and points to the sibling, and the fourth gives the no-data edge case. There is no filler or redundancy.

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, combined with the complete schema, annotations, and output schema, fully equips an agent to call this tool correctly. It explains the data source, unit eligibility, metric semantics, sibling differentiation, and edge-case behavior, so no critical information is missing for selection or invocation.

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 schema already covers 100% of parameters with descriptions and enums, so the baseline is 3. The description adds meaningful parameter-level context by clarifying what 'unit' means here (must have an urban area) and by explaining that all values except the count are percentages of that unit's urban dwellings. This goes beyond the schema's syntactic descriptions.

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 states a specific resource (HCP 2024 urban dwellings), scope (Morocco or units with an urban area), and the concrete metrics returned (counts, occupancy, type, age, materials, networks, shortfall). It explicitly distinguishes itself from get_indicators by clarifying that it counts dwellings, not households, which prevents sibling confusion.

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 names the closest sibling, get_indicators, and explains the key difference: this tool counts dwellings while get_indicators describes the dwelling each household lives in. It also states a clear exclusion boundary: 'A unit with no urban area has nothing here,' telling the agent when not to expect results.

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