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

Annotations already signal readOnly/idempotent/non-destructive behavior, so the description adds strong extra value: snapshot pinning, torn-read prevention, bare ID resolving to head, has_more pagination behavior, and the fact that embeddings are never returned. This goes well beyond annotation-derived knowledge.

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?

Purpose is front-loaded and the technical paragraphs are largely necessary for correct pagination. It is dense but not bloated; the snapshot/tearing explanation could be slightly more compact without losing essential meaning.

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?

Given the output schema exists, the description covers all behavior an agent needs: exact-ID reads, authorized access, pagination state, snapshot semantics, head behavior, and embedding exclusion. Nothing critical is missing for correct invocation.

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 covers all parameters, but the description adds meaning: memory_id can be a bare ID or revision, offset/limit are character-based paging controls, and continuation relies on returned revision/next_offset. Minor flaw: next_offset is not an actual input-schema property, so the agent must infer it should be passed as offset.

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 'Read one exact authorized XMemo memory in character windows' — a specific verb, resource, and mode. It clearly differentiates from siblings like recall/search by requiring an exact memory ID rather than performing search or fuzzy retrieval.

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?

Provides explicit guidance for the initial read (bare memory ID, offset 0) and continuation reads (revision as memory_id, has_more/next_offset), including why revision must be used. It does not explicitly name excluded sibling tools, but the context strongly implies this is for exact-ID reads after recall/search.

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