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

Annotations only declare readOnlyHint=true, so the description usefully adds that the memory is account-wide across all agents (not per-agent) and discloses the empty-state behavior — it returns a note when nothing is saved yet. It does not describe the shape or size of what comes back, but the empty-state and scope disclosures go beyond the annotation.

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 sentences, each earning its place: what the memory is, the reason to read it, and the scope plus empty-state caveat. Front-loaded with the resource definition rather than preamble.

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?

For a zero-required-param, read-only tool with no output schema, the description covers purpose, scope, and the no-data case — enough to call it correctly. It stops short of telling the agent what the returned memory looks like in practice, which would help an agent decide how much to trust it.

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 on_behalf_of is fully documented in the schema itself. The description mentions account scope but never connects it to the agency-client parameter, so it adds nothing beyond the structured field. Baseline 3 is correct here.

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?

Names the specific resource (the user's saved memory) and enumerates exactly what it holds — durable facts, preferences, and learned context. The scope note ('account-wide, not per-agent') further pins it down and separates it from per-agent reads like get_agent_details or query_agent_people.

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 clear use case: read it to ground a reply before asking the user to repeat themselves. No explicit when-not or named alternatives (e.g. search_chat_history, get_personalization_guide, get_writing_style_guide), so routing among the several 'read saved context' siblings is left to inference.

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