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

Annotations already declare readOnly, idempotent, non-destructive, so the safety profile is covered. The description adds context the annotations cannot: that the returned status is "invalidated" when the memory was forgotten, and that a share handle scopes the read to another user's data. It does not say what happens with a stale or unknown handle, which is the remaining gap.

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 dense sentences that front-load the action and the source of the input, then the cross-user variant. No filler or restatement of the title.

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 no output schema, the description carries the burden of describing return values and does so by listing the expanded fields and the meaning of status. Combined with a low-complexity two-parameter schema, this is nearly complete; only error/edge behavior for an invalidated or unrecognized handle is unstated.

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 only 50% — the handle property has a pattern but no description. The description compensates by defining handle as the value memory_search returned and by explaining share as the opt-in for cross-user reads, which is meaningful beyond the schema's regex constraint. It is not exhaustive on handle formatting but the pattern covers that.

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 one memory in full") plus the exact provenance of the input handle, and enumerates what is returned (title, summary, text, facts, relationships, status). This clearly separates it from the sibling memory_search, which produces the handle in the first place.

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?

The description establishes the workflow: it is the step after memory_search, operating on a handle that search returned. It also gives the branch condition for reading someone else's memory (pass share). It does not mention when not to use it or point to alternatives like memory_evidence or memory_turn_context, so it stops short of a full routing statement.

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