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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds ordering (newest first) and the shape of cross-references (@plasmid / !action / &gel), which is useful, but the enumerated return fields largely duplicate the output schema and it says nothing about permissions, pagination behavior, or result-size limits.

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?

Two sentences, front-loaded with the identity of the resource and its ordering before moving to filtering. The second sentence is long and carries both the filter list and the motivation, but each clause earns its place; no filler.

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?

With an output schema present, the description needn't explain return values, and annotations cover the safety profile. It covers purpose, ordering, and filtering well; the gaps are the undocumented _files/_subject project-reference parameters and any statement about how filters combine, which for a 6-parameter tool leaves a small hole.

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 tag, collection, search, and limit are already fully documented; baseline is 3. The description restates the three filter parameters and notes search matches title or body, but adds no information about whether filters compose (AND vs OR) or about the _files/_subject parameters, which are entirely absent from the description.

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 (list lab-notebook entries), plus scope details: ordering (newest first), the fields returned (id, title, tags, collection, modified time, cross-references), and the three filter axes. An agent can immediately tell this is the read side of the experiment notebook, distinct from the write-side sibling.

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?

Gives clear usage context — 'so a run can find the entry it is continuing instead of starting a second one about the same experiment' — which is genuine when-to-use guidance and implicitly steers away from creating a duplicate entry. It never names the alternative tool (e.g. record_experiment) or states exclusions explicitly, so it falls short of a 5.

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