stock

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

With no annotations, the description carries the burden and does well: it defines exactly what is counted (carried + storage + Dimensional Depot), what is deliberately excluded (machine buffers, crate contents) and why, and notes fluids are in m3. It does not state the read-only nature, error behavior for unknown items, or pagination/row-cap semantics beyond what the schema already says.

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 the core definition, and each subsequent sentence covers a distinct behavior (inclusions vs exclusions, where mode, units). Slightly dense and jargon-heavy ('Dimensional Depot', the affordability-check aside), and the stray ``where=True`` inline formatting is rough, but sentences generally earn their place.

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?

For a read-only query tool with no output schema, the description conveys enough about the shape of results (per-item totals, per-container rows with region/coordinates, summary line, fluid units). The unspecified parameters (save, world, offset) are the main remaining gap.

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 57%. The description meaningfully expands the `where` parameter (one row per container/crate with region and coordinate, summary line for carried/Depot) and clarifies the scope of the item list, but `save`, `world`, and `offset` have no description anywhere, and `as_of` only relies on its schema text. This is close to the baseline 3 for partial coverage.

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 opening line names a specific resource and scope: 'What you own, by item: spendable stock apart from what merely exists.' It even carves out a boundary against the related 'crates' tool by stating crate contents are excluded, which helps distinguish it. It stops short of naming which sibling to use for other views (e.g. storage, crates, search_items), so differentiation is partial rather than complete.

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 implicit in the semantics: it explains that 'where=True answers "and where is it"', which tells the agent when to flip that flag. However there is no explicit when-to-use-this-vs-alternative guidance among the many inventory-adjacent siblings (storage, crates, search_items, collected_from_world).

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