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

Annotations already flag the mutation/destructive profile, but the description adds context the annotations cannot: memories persist into the <team_memory> block of future conversations, are shared team-wide, and carry privacy/sensitivity constraints plus source-of-truth rules. This meaningfully exceeds the structured hints.

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?

Purpose is front-loaded in the first sentence, followed by definition then a rules block, so nothing is buried. It is on the long side and the closing sentence partially restates the trigger already implied earlier, but nearly every line carries actionable constraint.

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 still tells the agent where the stored memory surfaces (<team_memory>), who sees it (whole team), and the safety boundaries around what may be written. Nothing needed to invoke a save/update/delete correctly appears to be missing.

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%, so the baseline is 3, but the description goes further by specifying how content should be written (one short self-contained sentence, include relevant dates) and that update should be preferred over a duplicate save. It stops short of clarifying every field's edge cases, but adds real value beyond the 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?

The description names precise operations (save, update, delete), the exact resource (a team memory for a property), and defines what a memory is with concrete examples (fiscal year, campaign naming rules, KPIs). This clearly separates it from siblings such as search_memories, list_properties, or the annotation tools.

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?

It states exactly when to invoke the tool (user asks to remember, forget, or correct), what may and may not be saved, and directs the agent to check the <team_memory> block and prefer action=update over duplication. Exclusions and alternatives (search_memories, list_properties referenced in the schema) are covered.

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