Katzilla MCP

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

The description adds valuable behavioral context beyond what annotations provide. While annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true, and openWorldHint=true, the description adds: data source attribution ('Source: OpenAQ (CC-BY 4.0)'), update frequency ('updates daily'), and detailed return format information ('Returns the Katzilla envelope { data, quality, citation } — quality scores freshness/uptime/confidence; citation carries the source URL, license, and a SHA-256 data hash for audit'). This provides important operational context about data provenance and quality metrics.

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 efficiently structured in two sentences that each earn their place. The first sentence states the core functionality and filtering options, while the second provides crucial metadata about source, update frequency, and return format. There's zero wasted text, and important information is front-loaded appropriately for agent comprehension.

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 the tool's moderate complexity, rich annotations, 100% schema coverage, and presence of an output schema, the description provides excellent contextual completeness. It covers purpose, data source, update frequency, and detailed return format information. With annotations handling safety/behavioral aspects and the output schema presumably documenting the return structure, the description focuses appropriately on the value-added context that structured fields don't capture.

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?

With 100% schema description coverage, the input schema already fully documents all 4 parameters (lat, lng, limit, radius) with their types, constraints, and descriptions. The description mentions 'optionally filtered by coordinates and radius' which aligns with the schema but doesn't add significant semantic value beyond what's already in the structured fields. The baseline score of 3 is appropriate when the schema does the heavy lifting for parameter documentation.

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 specific action ('Search for air quality monitoring locations'), resource ('from the OpenAQ platform'), and scope ('optionally filtered by coordinates and radius'). It distinguishes itself from sibling tools by focusing specifically on air quality monitoring locations rather than other environmental data sources like weather, carbon intensity, or water quality tools in the environment category.

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 context about when to use this tool ('Search for air quality monitoring locations... optionally filtered by coordinates and radius'), but doesn't explicitly mention when NOT to use it or name specific alternatives. It implies usage for location-based air quality data searches, but lacks explicit exclusion guidance for other types of environmental queries that might be handled by sibling tools like environment__waqi or environment__openmeteo-aq.

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