memory_write

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

With no annotations, the description usefully discloses literal interpretation, rejection of instruction-like content, current-project scoping by default, and the session-level effect of pinning. It does not cover duplicate handling, overwrite behavior, or other write lifecycle details, but it goes well beyond merely implying that a mutation occurs.

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?

The description is compact and front-loaded with the operation, then moves efficiently through content constraints, validation, scope, and pinning. Nearly every phrase supplies actionable information, with no filler or repetition.

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?

It is sufficient for a basic content-only write and unusually clear about scope and pinning, but it is not complete for the full six-parameter interface. The undocumented optional fields and absence of duplicate, failure, or sibling-routing guidance leave meaningful invocation gaps.

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?

Despite 0% schema description coverage, the text substantially explains content, scope, and pinned, including scope syntax and defaults and the consequences of pinning. However, source, entities, and timestamp receive no semantics in either the schema or description, leaving half the parameters 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?

"Store ONE literal fact" gives a specific action, resource, and cardinality, while the examples—decision, bugfix, convention, gotcha, preference, and event—clarify the intended content. This readily distinguishes writing individual memories from siblings such as memory_recall, memory_list, and memory_consolidate.

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?

The description gives concrete usage constraints: store one literal fact, use explicit entities and absolute dates, avoid instruction-like content, and pin only when the user explicitly requires persistent remembrance. It does not explain when another memory sibling should be used instead, but the when-and-when-not guidance is otherwise strong.

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