get_tile_catalog

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

No annotations are supplied, so the description carries the full burden and does so well: it discloses the read-only nature, the output-limit behavior of the sheetless call, the source authority hierarchy (builtin/sidecar/project, manual outranking sidecar), autotile base-id semantics, and the `transparent` layer requirement. It omits error/invalid-tileset behavior and any pagination for very large sheets.

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 purpose is front-loaded, but the body is a dense run-on that front-loads the purpose then stacks source semantics, autotile notes, coverage scope, and the sheet rule into a single lengthy block. Much is useful, yet it is verbose for a two-parameter read tool and could be trimmed.

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?

With no annotations and no output schema, the description correctly assumes responsibility for explaining return values (source categories, confidence, manual flag, transparent flag, autotile base ids) and the output-size safeguard. An agent has enough to call and interpret the result.

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 description coverage is 100%, so the schema already documents both `sheet` and `tilesetId`, establishing the baseline of 3. The description elaborates on `sheet` (filename vs role, omit-for-summary) but adds little parameter-level syntax beyond 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+resource: 'Get the semantic tile catalog for a tileset', and immediately defines what the catalog contains (named tiles with representative ids, source, confidence). An agent can distinguish it from get_tilesets (lists tilesets) and describe_tile (one tile). It stops short of naming sibling alternatives explicitly, so it isn't a perfect 5.

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?

Gives concrete usage context: call without `sheet` for an index, pass `sheet` (filename or role) for full entries, and feed autotile base ids to a paint command. It does not state when NOT to use it or name a sibling tool to prefer instead, so it falls just short of explicit alternative routing.

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