Say what a tile id is

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

With readOnlyHint already declaring safety, the description adds substantial context beyond annotations: it explains the flags array semantics (directional passability, the 0x10 quirk in stock tilesets, ladder/bush/counter/vehicle/terrain bits) and discloses that contactSheet creates and deletes a scratch map, touching no tileset row or real map. That side-effect disclosure is exactly what annotations cannot convey.

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?

Front-loaded with what the tool reads, then the query modes, then the contact sheet caveat. Every sentence carries information, but the dense em-dash prose runs long and could be split for scannability.

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?

There is no output schema, so the description carries the full burden of describing return values — and it does, enumerating every field of an entry and what the contact sheet draws. For a 6-parameter tool with a nested object, nothing an agent needs to call it correctly appears to be 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?

Schema coverage is already 83%, so the baseline is 3, but the description adds real meaning: it explains the slot grouping (A1–A4 autotile shape groups of 48, A5/B–E fixed), what mapId vs tiles vs slot each retrieve, and that tilesetId defaults to the map's own tileset. Minor gaps remain, such as the interaction between limit and the various modes.

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 — reading the tile dictionary as the engine reads it — and enumerates exactly what each entry carries (slot, bound image, layer, flags semantics, usage counts). It is clearly distinguishable from siblings like tileset_slots, inspect_cell and render_map.

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 lays out four query modes and when each applies: mapId 'for every tile a map really paints, which is the fastest way to learn an unfamiliar tileset', tiles for ids in hand, slot to walk a slot pattern-by-pattern, or neither for the slot table alone. contactSheet is also positioned as the answer for visual questions.

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