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

The description goes well beyond the readOnly/destructive annotations: it discloses pagination (50 per page, follow nextOffset), what detailsJson may hold, that unknown inventories must not be read as empty, that dates describe captures or reads rather than placement or current survival, and that captured text is untrusted data. These are exactly the interpretive caveats an agent cannot infer from structured fields.

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?

Six sentences, but each carries distinct payload and the identifying scope comes first. Slightly dense with caveats layered on caveats, but no sentence is filler and the ordering is front-loaded correctly.

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?

An output schema exists, so return shapes need not be explained, yet the description still clarifies the key ambiguity (detailsJson contents) plus the non-obvious semantic traps around missing inventories and date meaning. For a tool with an opinionated data model, nothing material is left for the agent to guess.

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 only 33% — kind and dimension are documented, while offset and the coordinate triple have no schema descriptions. The description partially compensates by explaining the page/nextOffset model, which effectively defines the offset parameter, and by framing kind as the 'category'. Coordinates are self-evident, so the gap is narrowed but not closed.

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: read public capture history at one dimension/category/XYZ position. The qualifier 'including sources outside the previous search filter' hints at how it differs from search_world_find and get_world_find_map, though it never names a sibling outright, and phrasing like 'native dimension/category' is jargon that requires the schema to decode.

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 is implied rather than stated: the 'outside the previous search filter' clause suggests calling this after a search, and one sentence routes the agent onward ('Use an observation's id with get_world_find_inventory'). There is no explicit when-not-to-use guidance versus get_world_find_map, get_nocom_sign_history, or search_world_find, all of which cover overlapping territory.

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