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

Annotations already declare readOnlyHint=true and openWorldHint=false, and the description adds genuinely new behavior: bodies over 40,000 characters are not returned in full but come back as an outline, with section/page as the means to drill in. It also discloses that a rev_id is returned and should be reused as base_rev_id on the next write, which is non-obvious chaining context. It does not say what a normal under-limit read returns verbatim, so it is not exhaustive.

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?

The purpose and the pointer-discovery prerequisite are front-loaded in the first clause, followed by the large-body behavior and the revision-chaining advice. Two sentences plus a parenthetical carry a lot with no filler, though the telegraphic phrasing ("read a section (heading path or JSON pointer) or page=0,1,...") is dense enough to require a second read.

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, so the description correctly spends its words on return behavior: outline for oversized bodies, section/page drill-down, and rev_id for later writes. For a five-parameter read tool this covers what an agent needs to call it correctly; only the exact shape of a normal full-body return is left implicit.

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 100% and each parameter is already documented, so the baseline is 3; the description earns above that by tying rev_id to the downstream base_rev_id parameter, which the schema alone does not convey. Its note that section accepts a heading path or JSON pointer and that page enumerates 0,1,... largely restates the schema, adding modest value.

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 ("Read an artifact by its pointer memory id") and immediately makes clear it is the read-side counterpart to artifact_write by mentioning base_rev_id on writes and pointing at memory_retrieve for discovering pointers. An agent can distinguish it from artifact_history, artifact_orphans and memory_retrieve without opening any 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?

Gives a concrete prerequisite workflow (call memory_retrieve on a pointer to get the artifact block, head_rev_id and outline) and explains what to do when the body is large: read a section or use page=0,1,... It does not explicitly exclude sibling alternatives such as artifact_history or say when a revision read instead of a head read is warranted, so it stops short of full when/when-not coverage.

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