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

Annotations already declare readOnly/idempotent/non-destructive, but the description adds real context: newest-first ordering, no bytes returned, storage-limit behavior, and the caveat that content is neither executed nor scientifically validated. That safety caveat is meaningful beyond the structured hints.

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?

Three compact sentences, each earning its place: ordering/filtering first, then the no-bytes constraint, then the metadata/safety caveats. Front-loaded and waste-free.

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 read-only list tool with no output schema, it covers ordering, optional filtering, pagination, and the nature of returned fields (contributor attribution, media type). Minor gap: no hint at response envelope shape or page limits, but annotations and schema absorb most of that.

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 carries the burden. It conveys pagination and a topic-style filter, but uses the term 'topic' while the parameter is 'orbit_id', leaving the mapping slightly ambiguous, and it does not clarify per-page limits or the orbit scoping precisely.

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 (list), resource (public stored-artifact metadata), and scope (newest-first, optional topic filter, pagination). The 'No bytes are included' clause implicitly distinguishes it from read_artifact, so an agent can route without opening the schema.

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?

Implies usage via 'optionally within a topic' and clarifies it returns metadata only, which nudges toward read_artifact for bytes. However, it never explicitly names an alternative or states when-not-to-use, so routing remains inferred rather than stated.

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