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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so safety and locality are covered; the description usefully confirms the corpus is bundled/local and that each entry carries format, size and archive provenance. It does not disclose the default cap of 50, the presence of a `total` count, or whether the list is exhaustive or windowed — pagination behaviour is left entirely to the schema.

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 front-loaded sentence that leads with the action and resource before the parenthetical inventory. The long embedded list of file types and the trailing 'where the corpus records one' qualifier add bulk, but nothing is strictly redundant.

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?

An output schema exists, so return-value explanation is unnecessary, and the safety profile is handled by annotations. What is missing for a discovery tool in this very large sibling set is relational context: how samples relate to load_record, list_library, list_traces, or the `sample` field of other tools. The definition is adequate but leaves the agent to work out the workflow.

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 100%, so the kind, limit and query parameters are already fully documented with examples and semantics. The description adds nothing about filtering (e.g. that `query` terms must all match across id/name/category/format) and even the enumerated formats overlap with but do not map cleanly onto the `kind` vocabulary. Baseline 3 applies.

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 gives a specific verb and resource — browsing the bundled sample library — and enumerates what the corpus contains (GenBank and SnapGene plasmids, FASTA sets, alignments, Sanger traces, structures, variant calls), plus what each entry reports (id, format, size, provenance). An agent can tell this is a read-only catalogue of bundled files. It does not, however, distinguish itself from near-siblings like list_library, list_databases, list_traces or search_records, so the differentiation is only partial.

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?

Usage is only implied: 'a new project can start from' hints at discovery/bootstrap use, but there is no explicit statement of when to choose this over list_library, list_traces, search_records or fetch_record, and no mention that the returned ids feed the `sample` field of other tools. The agent must infer the routing.

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