Write memory

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

Annotations already declare the write/idempotent/destructive profile, and the description adds substantial context beyond them: automatic versioning readable via get_memory_history, the memory:write vs memory:propose permission model, and that a proposal stays pending_review and changes nothing until approved. This is exactly the extra behavioral detail an agent needs for a mutating tool.

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?

Front-loaded with the core verb+resource and versioning behavior, then param and permission details. Mostly every sentence earns its place, though the is_archived clause largely repeats the schema description and the final playbook_id sentence restates the schema's UUID/GUID wording.

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 the complex parts well for a 14-param tool: auth/permission model, versioning, proposal workflow, and archiving. With no output schema, it stops short of saying what the call returns (e.g., the stored key or entry), which is the remaining gap.

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 adds genuine meaning: memory_at defaults to save time and accepts an ISO timestamp to backdate, is_archived toggles visibility, and tier controls context priority independently of archiving. These clarify interactions between parameters rather than restating schema text.

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+resource ('Create or update a memory by key') and immediately distinguishes it from the read side by naming get_memory_history for version history. An agent can tell it apart from read_memory, delete_memory, and archive_memories without opening a schema.

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 clear conditional context: is_archived for hiding/restoring, memory:propose for proposal-mode writes, and playbook_id for targeting. However it never explicitly routes between the sibling mutation tools (archive_memories, promote_memory, consolidate_memories), leaving that comparison to inference.

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