Raw ArcGIS query

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

No annotations are provided, so the description carries the full burden. It discloses that field names are the layer's own rather than normalized, and recommends querying where='1=1' limit=1 to inspect a record, which sets expectations about raw output. It could say more about read-only guarantees or error modes, but the main behavioral quirk is covered.

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?

Three sentences pack the tool's purpose, usage context, and field-name caveat without redundancy. The inline example 'where='1=1' limit=1' is a compact, actionable illustration.

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 an escape-hatch tool with no output schema and no annotations, it gives an agent enough to call it correctly: how to choose source keys, how to discover valid fields, and what kind of filters it supports. Minor gaps remain around exact response shape and behavior when SQL is invalid, but the critical invocation steps are present.

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 60% of parameters with descriptions (where, source, out_fields). The description adds beyond the schema by advising list_sources for source keys and explaining that where-clause field names are raw and can be discovered via a probe query. It doesn't elaborate on limit/offset, but those are constrained with defaults in the schema.

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?

States a specific verb and resource: 'run a raw SQL-92 WHERE clause against one source's ArcGIS layer and get raw attributes back.' The 'Escape hatch' framing differentiates it from sibling search tools, making its role in the family immediately clear.

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?

Explicitly positions itself as a fallback: 'filters the normalized search does not cover (dates, depths, cumulative production).' It also directs the agent to list_sources for valid source keys and suggests a field-inspection technique, so when to use it and what to do first are clear.

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