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

Annotations already declare non-read-only, non-destructive, non-idempotent, closed-world, so the safety profile is covered. The description adds real value beyond that: facts are durable across conversations and an existing memory can be corrected rather than duplicated, which is not derivable from the annotations. It stops short of saying what comes back (e.g., a new memory id for later forget/list) or any limits on size/count.

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 sentences, no filler: the core action and scope constraint lead, the correction path follows, and the prohibition list closes. Every clause carries distinct information.

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?

Covers purpose, exclusions, and the update/duplicate-avoidance path for a 5-required-param write tool with no output schema. The remaining gap is that it never explains how to choose among the 'kind' enum values, which is the main semantic decision the caller must make.

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?

With 60% schema description coverage, the schema already documents about/validUntil/replacesMemoryId, and the description only reinforces replacesMemoryId's correction semantics. The required 'kind' parameter with five enum values (IDENTITY, PREFERENCE, STANDING_RULE, LINK, TEMPORARY) has no description in the schema and none here, and 'value' is likewise unexplained, so a key decision point is left undocumented.

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?

Specific verb and resource ('Save one durable fact') plus the triggering condition ('when the person asks SkipCalls to remember it for future conversations'), which separates it from automatic data capture. The correction clause (pass replacesMemoryId) further pins down scope, and the exclusion sentence implicitly distinguishes it from knowledge pages, notification settings, reminders, and contacts.

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 when-to-use trigger, an explicit when-not-to-use list (call-handling rules, notification settings, one-off tasks, customer details, sensitive data), and names the mechanism for the correction case. An agent can decide invoke vs. skip vs. correct without opening the schema.

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