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

Annotations declare non-read-only, non-idempotent, open-world behavior; the description adds genuinely new context by disclosing the two special response states (clarification, outOfScope) that an agent must handle. It omits whether removed layers are recoverable or whether edits are undoable, which matters for a mutating tool.

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?

Four tight sentences, front-loaded with the core action, then valid mutations, then the two exceptional response paths, then the doc pointer. No filler or restatement of the tool name.

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?

Covers scope, ambiguity handling, out-of-scope routing, and defers the Op grammar to a named resource, which is complete for a natural-language mutation entry point. No output schema exists, so return shape relies on the description, which only partially names the emitted fields (clarification, outOfScope) rather than the full success response.

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 coverage is 100% and all three parameters (map_id, instruction, rationale) are documented in the schema with examples and constraints. The description adds no parameter-level syntax or format guidance beyond what the schema already provides, so baseline 3 applies.

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+resource ('Apply a natural-language instruction to an existing workspace') and enumerates the exact mutation scope (filter/remove layer, camera, basemap). This distinguishes it from atomic siblings such as filter_layer, remove_layer, and set_camera, which do the same work one operation at a time.

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?

Explicit routing rules: ambiguous instructions yield a clarification field, unrelated instructions yield outOfScope and the agent should 'build a new map in that case', naming the alternative sibling. It also points to the resource documenting the full Op catalog and predicate grammar.

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