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

Annotations already declare readOnly, idempotent, non-destructive and openWorld, so the safety profile is covered. The description adds only a resource label and does not explain the significant behavioral fact that the result set is filtered to on-disk packs by default, nor how large the listing may be or whether it touches a remote registry (implied by openWorldHint).

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?

It is a single short sentence with no filler, which is good, but it is a sentence fragment rather than a front-loaded verb+object statement, and its brevity comes at the cost of missing scope information rather than from efficient packaging.

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 output schema exists, so return values need not be described, and the tool is structurally simple (one optional boolean). Still, an agent gets no guidance on the default on-disk filtering, no sense of how this feeds the pipeline/experiment workflow, and no differentiation from the many sibling catalog and data tools.

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 single parameter only_on_disk is fully documented in the schema (100% coverage), including the default and the meaning of both values, so the description has no compensating work to do. Baseline 3 is appropriate since the description mentions nothing about filtering behavior.

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?

"Curated public EEG datasets (MOABB packs) available to pipelines" identifies the resource and adds domain qualifiers (curated, MOABB packs, pipeline-usable), but it is a noun phrase with no verb — the listing action is only conveyed by the title. It does not distinguish itself from nearby catalog siblings such as catalog.nodes or catalog.templates beyond the noun.

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?

There is no indication of when to call this versus alternatives (e.g. data.inspect_dataset for a specific dataset, or catalog.template for pipeline definitions). No prerequisites, no mention of what a downstream pipeline does with these identifiers. The agent must infer everything from the name.

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