bw_update_query_characteristic

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It reasonably discloses the important behavioral traits: applying to every characteristic with '*', accepting 'default' to fall back, applying all specs in a single save, and requiring the characteristic to already exist in the layout. It does not describe output/response or rollback behavior, which prevents a 5.

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 front-loaded with the core action and product, then packs the key variants of the trait into a long but informative list. It contains no real filler, although the run-on enumeration and the slight overgeneralization about 'default' keep it from being a model of discretion.

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?

The definition is complete enough for a complicated tool with a rich input schema: it explains the wildcard infoobject, the meaning of 'default', the single-save behavior, the necessity of a prior layout, and the need for technical names. It is less complete about the return contract or what happens after a failed save, but the operation itself is clearly described.

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?

The input schema already provides full descriptions for all parameters, so the description did not need to compensate heavily. It does add useful shorthand about 'default' and '*' semantics, but the statement that 'Every property also accepts default' is overbroad because the schema excludes 'default' from several enums items such as text_type and sorting.direction. Because schema coverage is 100%, the baseline is appropriate.

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 description starts with a concrete verb-resource pairing: 'Set the display and access properties of the characteristics in an existing BW Query.' It enumerates the exact property groups affected (result rows, display as key/text, access type, sorting, etc.), which distinguishes it from related update tools like bw_update_query_layout, bw_update_query_key_figures, and bw_update_query_settings.

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?

It states an explicit precondition: characteristics must already exist in the layout, and routes the agent to bw_update_query_layout if they need to be added first. It could be stronger by naming the alternative tools it should not be used for, but the very-specific scope ('characteristics' in a query layout) provides enough usage direction.

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