ds_add_avus

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

With no annotations, the description carries the full burden. It usefully discloses a cross-system side effect — mirroring all AVUs into DuckLake as ONE snapshot — which is genuinely non-obvious from the schema. However, it omits critical behavior for a mutation tool: required permissions, what happens on partial failure (atomicity of the snapshot vs the AVU write), and duplicate-attribute handling.

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?

A single front-loaded sentence that conveys batch semantics, the mirroring side effect, and the efficiency motivation with no filler. Nothing could be trimmed without losing information.

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?

There is no output schema or annotation coverage, so the description must stand alone. It covers purpose and the dual-write behavior but leaves return values, error/partial-failure semantics, and duplicate handling unspecified — adequate for the happy path, thin for a two-system mutation.

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 67%, so most parameters are documented in the schema itself (target as an iRODS path, avus as batched AVUs). The description adds only the detail that target may be a data-object or collection, and says nothing about the unit field or target_type beyond defaults. Baseline 3 is appropriate given the schema does most of the work.

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 names a specific verb (add), resource (AVUs), and scope (MULTIPLE AVUs to one data-object/collection in a single call), which clearly sets it apart from the singular ds_add_avu sibling by emphasizing the batched nature. It stops short of naming the sibling, so the differentiation is inferential rather than explicit.

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?

'efficient bulk tagging' implies when this tool is preferable (large AVU sets, single snapshot), but there is no explicit when-to-use/when-not guidance and no pointer to ds_add_avu for single-AVU cases. Usage is implied rather than stated.

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