storage

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

With no annotations, the description carries the full burden and discharges much of it: it defines exactly which container classes count as stock, explains that fill is computed rather than read from the save (used slots / slots, m3 over class capacity), and discloses the '-' sentinel for unknown values. It omits other behavioral facts an agent would want, such as which save/world is used by default and any auth or rate considerations.

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 one-line summary is front-loaded and the subsequent paragraphs are organized around inclusion, ordering, and metric definition. The prose is a little long and spends words on exclusions that could be tighter, but every sentence carries distinct information rather than restating the schema.

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 an 11-parameter query tool with no output schema and no annotations, the description explains the key derived field (fill), the row ordering, and what counts as a row, which is genuinely useful. However it never describes the shape of a returned row beyond fill, and leaves near/radius_m, save/world defaulting, and pagination (limit/offset) unexplained, so an agent cannot fully predict the response.

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 64%, so several parameters (save, world, offset, radius_m) are documented nowhere. The description reinforces the item parameter and the ordering it triggers, but says nothing about near/radius_m pairing, container_kind, or how save/world are defaulted. Baseline 3 is appropriate given the schema does most of the work and the prose adds only marginal meaning.

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 gives a concrete triple of what it returns (which container holds what, where it stands, how full), and the second paragraph sharpens the scope by explicitly excluding splitters, mergers, and machine buffers. That is much clearer than a bare noun name. It loses a point because it never distinguishes itself from nearby siblings such as stock or crates, leaving the agent to infer the boundary.

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 only implied through scope and ordering: 'fullest first, or by how much of item they hold when one is named' suggests a survey/audit use case. There is no explicit when-to-use or when-not, no statement of prerequisites, and no named alternative (stock, crates, factory_query) for the cases this tool does not cover.

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