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

Beyond annotations (readOnlyHint=false, destructiveHint=false), the description adds key behaviors: emits ordinary undoable ops, costs 1 credit on mutation, clarifications are refunded, returns a grounded summary like 'kept 37 of 150 features', and never guesses geometry for unresolved names. This is rich, actionable context.

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 a single dense paragraph, but every sentence carries operational value—credit cost, undoability, clarification behavior, and output summary. It is front-loaded with purpose and free of filler.

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?

No output schema exists, but the description covers return behavior ('grounded summary', 'clarification with real nearby candidates'), side effects (undoable ops, credit cost), and constraints (names only). For a tool with five parameters and three areaRef variants, this is complete enough for an agent to select and invoke 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?

With schema coverage only 40%, the description compensates by explaining the areaRef variants with examples ('Broadway from Arbutus Street to Main Street', 'Mount Pleasant', intersection surroundings) and the 'names only' rule. It does not elaborate on bufferMeters/radiusMeters, but those are fairly self-explanatory and partially documented 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?

The description opens with a specific verb and resource: 'Refine an existing layer to a NAMED area the server resolves from OpenStreetMap.' It clearly distinguishes from siblings like filter_layer by highlighting the named-area resolution and the three modes (filter/select/clip) that produce different outcomes.

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 gives explicit guidance: 'Pass names only, never coordinates' and explains that unresolvable names return a clarification with real candidates. It doesn't explicitly exclude alternatives, but the context implies when this tool is appropriate (refining an existing layer to a named area) versus generic filtering.

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