write_memory_tool

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

With no annotations, the description carries the full burden and discloses key behaviors: atomic write, the return shape, and that ttl_seconds is stored but not enforced. This goes beyond a simple 'writes a value' statement and provides useful operational detail, though it omits error handling and file existence behavior.

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 two sentences, directly front-loaded with the primary action. Every sentence adds value: the first states the operation and atomicity, the second explains the return value and ttl_seconds caveat. There is no wasted verbosity.

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?

Given the tool's simplicity and the presence of an output schema, the description covers the core behavior (write, atomic, return) but lacks context on parameter semantics and usage scenarios. It is adequate but has gaps in explaining repo_path and when to choose this tool over siblings.

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%, so the description must explain parameters. It only clarifies ttl_seconds (accepted but not enforced). The meanings of key, value, and repo_path are not explicitly described, although 'value' is somewhat inferable from 'Write a value'. This leaves room for ambiguity, especially for repo_path.

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 clearly states the tool writes a value to a specific file atomically, with a distinct verb and resource. It differentiates itself from siblings like read_memory_tool by focusing on writing. The inclusion of the return object further clarifies the operation.

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 implies usage (writing to reforge-state.json) but does not explicitly state when to use this tool over alternatives like read_memory_tool. There is no exclusionary guidance, so it earns a mid-range score.

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