pbi_set_relationship_direction

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

With no annotations provided, the description takes on the burden of disclosing side effects and operational nuances. It warns that changing to 'single' may alter totals that depended on bidirectional filtering, and advises verifying the report afterward. It also explains the temporary disablement of mode='both' and the distinct requirements of 'live' vs 'pbip' modes. This is above-average transparency, though it does not mention permissions or reversibility.

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 organized: a one-sentence purpose, followed by detailed parameter semantics in a code block. The caution about direction='both' and mode='both' is valuable but adds density. Every sentence serves a purpose, though the mode explanation could be clearer for non-experts. Overall, it is appropriately sized for the tool's complexity.

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 description addresses key behavioral aspects (direction side effects, mode behavior) and there is an output schema to explain return values. However, it does not clarify how relationships are uniquely identified when multiple relationships exist between the same two tables, and it does not explain the purpose of 'request_id'. Given the moderate complexity and lack of annotations, the description is mostly complete but has notable gaps.

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 schema has 0% description coverage, so the description must compensate. It explains the 'direction' parameter ('single' vs 'both') and the 'mode' parameter (live vs pbip, including the constraint that mode='both' is disabled). However, it does not explain 'from_table' and 'to_table' beyond their names, nor does it mention 'request_id' at all. Some parameters are self-explanatory, but the incomplete coverage warrants a mid-range score.

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 opens with a specific verb and resource: 'Cambia el filtro cruzado de una relacion' (changes the cross-filter of a relationship). This clearly distinguishes the tool from siblings like pbi_list_relationships (which lists relationships) and pbi_set_column_visibility (which changes column visibility). No ambiguity about what the tool does.

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?

The description implies usage by stating the action and explaining parameter values, but it does not explicitly state when to use this tool versus alternatives (e.g., when a relationship exists but needs its cross-filter direction changed). No exclusions or alternative recommendations are provided. The 'No confundir' note is a caution about parameter naming, not about when to use the tool.

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