get_tile_catalog

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

With no annotations provided, the description carries full responsibility and succeeds. It discloses read-only nature, the output-limit behavior for omitted sheet, autotile returning base tile id only, the 'transparent' flag meaning and practical implications, and the trust metadata (source, confidence, manual). It even explains coverage omissions. This is exemplary behavioral disclosure.

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 long but every sentence carries substantive information. It is structured logically: purpose, data fields, autotile behavior, coverage, sheet parameter usage, and transparent flag. The bolding of the critical sheet guidance improves scannability. No filler or redundancy observed.

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 and annotations are absent, so the description must self-document the return behavior. It does so thoroughly: return fields (source, confidence, manual, transparent), edge cases (autotile, uncovered sheets), output-limit behavior, and practical usage (feed to paint command). The description is fully sufficient for an agent to 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?

Schema coverage is 100% and both parameter descriptions are already detailed. The description adds meaningful context beyond the schema by explaining the rationale for the output limit ('to stay within the tool-output limit') and clarifying the per-sheet index content ('name + entry count'). It also reinforces the sheet role/filename usage. This raises it above the baseline 3.

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?

Purpose is explicit and specific: 'Get the semantic tile catalog for a tileset', clearly identifying the action (get), resource (tile catalog), and scope (per tileset). It distinguishes itself from sibling tools like describe_tile or find_tile by focusing on the catalog-level structure and semantic labels, including source, confidence, and transparency metadata.

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?

Usage guidance is strong: the description explicitly instructs 'Called WITHOUT `sheet` it returns only a per-sheet index... Pass `sheet` (filename 'World_A2' or slot role 'A2') to list one sheet's actual tile entries.' It also notes coverage ('Covers the default Overworld tileset... still-uncovered sheets are omitted'). However, it does not explicitly name alternative tools or say when NOT to use this tool, so only a minor gap remains.

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