diff_models

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

With no annotations, the description carries the full burden. It does convey that this is a passive read/compare operation and sketches the return shape (added/removed/modified buckets), which is useful. It says nothing about prerequisites such as whether the PBIP paths must exist locally, whether a connection via connect_target is needed, cost on large models, or error behavior for invalid paths.

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 one-line purpose, then usage triggers, then args, then returns — an agent can stop reading after line one. The Returns block is somewhat redundant given that an output schema exists, but it is short enough not to be wasteful.

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 two-parameter comparison tool with an output schema and no annotations, the description covers purpose, triggers, parameter meanings, and result categories. The main missing piece is prerequisite/setup context relative to siblings like connect_target, which an agent would have to infer.

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 0%, so the description must compensate — and it does, naming both params and defining role and type ('before: Path to the baseline PBIP directory', 'after: Path to the target PBIP directory'). It does not specify path format expectations (absolute vs. relative) or whether the directories must already be materialized, leaving a small gap.

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: 'Compare two semantic models and report structural differences', then enumerates exactly which artifact classes (tables, columns, measures, relationships) are diffed. No sibling tool does version-to-version comparison, so an agent can route here unambiguously.

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?

Explicit trigger conditions are given: comparing two versions of a Power BI model/PBIP directory, or seeing what changed between branches or releases. It stops short of naming alternatives (e.g., audit_model_and_report or plan_change) or stating when not to use it, so it lands just below the top mark.

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