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

Goes well beyond the annotations by disclosing that memory contents are sent to a third-party language model in the United States, gated behind a specific user setting, plan tier, and a daily quota, and that the call is refused with an explanation when the setting is off. Annotations cover only the read-only/idempotent safety profile; the data-sharing and quota details are exactly the context an agent cannot get from structured fields.

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, front-loaded with what the tool produces before the conditional constraints. The privacy/quota sentence is long but every clause carries decision-relevant information (vendor, jurisdiction, setting, plan, quota, refusal behavior), so little is wasted.

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 two-parameter generation tool with no output schema, the description is nearly complete: it says the output is a short summary and what inputs shape it. The only mild gap is not describing the summary's form or length beyond 'short', but no output schema exists to lean on, so a small deduction is fair.

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 0%, so the description must carry the burden. It does: 'focus' is identified as optional ('with an optional focus') and 'project' is explained through the '(or the whole memory)' clause, which tells the agent that omitting it widens scope. Both parameters gain meaning beyond the bare string types and empty-default schema.

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: writes a short summary of saved memories, scoped to a project or the whole memory, with an optional focus. The scope distinction (project vs. global) is clear enough that an agent can select it without opening the schema, though it does not name which sibling to use instead.

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 operational conditions (requires 'AI tagging and grouping' enabled, paid plan, 20/day cap, refused otherwise) but no guidance on when to prefer this over memory_search, memory_get_project_context, or memory_timeline. The agent learns when the call will fail, not when it is the right choice.

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