List Entities

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

With readOnlyHint=true already covering safety, the description adds substantial behavioral insight: the large per-entity payload cost, the role of bounding_box in that cost, the fact that plain list mode cannot communicate truncation, and that only compact mode reports total, truncated, and next_offset. This goes well beyond the annotations and helps the agent anticipate performance and pagination behavior.

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 front-loaded with the core purpose, then return shape, then the most important performance caveat, then a concrete usage example, then the paging subtlety. Every sentence carries actionable information; the length is justified by the tool's complexity and the need to warn about expensive results and truncation behavior.

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?

The description covers filters, return fields, field projection, nested properties, performance characteristics, the two result shapes, paging edge cases, and downstream usage of returned handles. An output schema exists and readOnlyHint is declared, so the description does not need to restate return-value structure or safety. Nothing important for selecting and invoking this tool correctly is missing.

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?

The input schema already documents all six parameters with 100% coverage, so the baseline is 3. The description adds meaning beyond the schema by explaining why fields projection matters, giving a concrete example with layer_filter, fields, and compact, and clarifying exactly which result envelope supports truncation reporting. This is useful semantic guidance layered on top of an already-complete 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: 'List entities in the drawing with optional type and layer filters.' It immediately states what is returned (handle, type, layer, color, type-specific properties) and how handles flow into sibling tools like entity_get, entity_move, and entity_delete. This fully differentiates it as the general entity-listing tool.

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 gives strong practical context: it warns that entity_list is the most expensive server result, shows exactly when to use fields and compact, and explains the paging limitation. It also tells agents to pass returned handles to downstream entity operations. It stops short of explicitly naming alternative list-like tools or saying 'use X instead when...', so it is clear but not exhaustive.

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