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

Annotations already cover the read-only, idempotent, non-destructive profile, and the description adds the substantive behavioral claim that the access policy is deterministic and that AI classification is metadata only and never grants access. That last point is real value beyond structured fields, though nothing is said about what happens for a missing or unknown memory id.

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 tight sentences, with the trigger condition front-loaded ahead of the return description and the access caveat. No filler, though the phrasing is dense enough that the caveat could be easy to skim past.

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?

An output schema exists, so return shape need not be explained, and the description covers when to call it plus the key trust boundary about AI classification. What is left out, error or not-found behavior, is minor for a read-only single-id lookup.

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% with a single required memory_id already documenting the optional 'mem_' prefix in the schema. The description adds no further meaning about the parameter, so the baseline 3 applies.

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 ('explain'/'returns') and enumerates the returned facets: deterministic access policy, sensitivity, audience, and classification provenance. This distinguishes it well from get_memory, though the distinction is implied rather than stated by naming the sibling.

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 an explicit trigger: 'use this when the person asks why they can see a memory, or who else can.' That is a clear activation condition, but it does not name alternatives such as change_scope or change_sensitivity for actually modifying visibility.

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