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

The annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the "Read-only." sentence mostly restates structured data. The genuinely additive part is the return contract ("Returns the memory object, or null if not found"), though an output schema exists. Nothing explains the non-obvious behaviors of the nested follow_chain traversal (returning the live terminal rather than the seed), include_deleted, or include_revisions, which are the real behavioral risks here.

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 short sentences, front-loaded with the operation and ID formats before the return contract. Nothing is padded, though "Read-only." duplicates an annotation and is the one sentence that does not earn its place for an agent reading structured fields.

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?

The high schema coverage and the presence of an output schema mean most of the burden is already carried elsewhere, and the description correctly covers the null-on-miss case. However, this is a moderately complex tool with a nested supersession-traversal object and soft-delete/revision toggles, and a one-line description leaves an agent without a model of what changing those flags actually does.

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 every one of the 7 parameters is already documented in the input schema, including the follow_chain sub-object. The description adds only the short_id format hint for memory_id, which is a marginal gain over the schema. Baseline 3 is appropriate when the schema carries the parameter burden.

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 ("Retrieve a single memory by ID") and illustrates accepted ID formats (UUID or short_id like mem-1a), which lets an agent distinguish it from the ID-less siblings memory_search and memory_list. It stops short of naming those siblings explicitly, so the differentiation is inferable rather than stated.

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: an agent can deduce this is the tool to reach for when it already holds a memory ID and wants a single record rather than a search. There is no explicit guidance on when to prefer memory_search or memory_list, and nothing about when the team or follow_chain options are appropriate.

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