memory_write

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

With no annotations provided, the description carries the full burden and does meaningful work: it discloses that the memory model reads content literally, that instruction-like content is rejected, and that pinned notes surface every session. It omits permissions, idempotency, and what a successful write returns.

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?

Four short sentences, front-loaded with the core purpose and constraints, with no filler. Density is high but each sentence carries a distinct rule; the trailing pinned clause could arguably be folded into the scope sentence.

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 6-parameter mutation tool with zero annotations and no output schema, the description covers the essential authoring and scoping behavior but leaves several parameters and the write result unaddressed. Adequate to call it correctly for the common case, incomplete for the full surface.

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 0% across 6 parameters, so the description must compensate. It explains content (one fact, literal phrasing), scope ('global' or 'project:<name>'), and pinned semantics, and hints at entities/timestamp via 'explicit entity names and ABSOLUTE dates', but leaves source and the entities/timestamp formats entirely 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?

The description opens with a specific verb+resource ('Store ONE literal fact') and enumerates the accepted fact types (decision, bugfix, convention, gotcha, preference, event), which sharply separates it from memory_consolidate or memory_recall. It does not name any sibling explicitly, so an agent must still infer that memory_pin exists for pinning rather than using the pinned flag here.

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 gives concrete authoring rules (explicit entity names, absolute dates, no relative dates) and one conditional trigger for pinned=True. However, it never states when NOT to use this tool versus siblings such as memory_pin, memory_consolidate, or memory_pending_synthesis, leaving the routing ambiguous.

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