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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so safety is covered. The description adds return behavior ('Returns attribute rows (and geometry)') and parameter behavior (SQL-like where, comma-separated out_fields), plus a sampling tip. No contradictions.

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?

Two sentences, front-loaded with the core action, and includes all key aspects (parameters, return, usage tip) without 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?

For a read-only query tool with 6 params and no output schema, the description covers the purpose, return type (rows and geometry), required context (URL from search_datasets), and provides a sampling idiom. This is sufficient for an agent to invoke it correctly.

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 covers all 6 params with descriptions (100%), so baseline is 3. The description adds meaningful usage guidance: SQL-like where syntax, comma-separated out_fields, and the sampling pattern where="1=1" and out_fields="*", which clarifies default behavior and gives a practical example.

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 'Query an ArcGIS Feature Service / Map Service layer by its url' – a specific verb and resource. It distinguishes from siblings by tying to search_datasets and specifying ArcGIS layers, making it clear this queries data rather than metadata or other services.

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 instruction 'from search_datasets' tells when to use it – after obtaining a layer URL from that tool. The tip 'Use where="1=1" + out_fields="*" to sample' provides a concrete usage scenario. However, it does not explicitly name alternatives or when not to use it.

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