agentmem

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

No annotations are provided, so the description carries the full burden. It discloses key behavioral traits: the tool saves state for future sessions and that loading is automatic, which is useful context. However, it lacks details on persistence (e.g., storage location, durability), permissions, or error handling, leaving gaps for a mutation tool with no annotation coverage.

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 highly concise and front-loaded: the first sentence states the core purpose, followed by specifics on what to capture and the automatic loading behavior. Every sentence adds essential information without redundancy, making it efficient and well-structured.

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 no annotations, no output schema, and 2 parameters with 50% schema coverage, the description is moderately complete. It covers the tool's purpose, usage timing, and parameter semantics for 'summary,' but lacks details on 'tags,' output format, error cases, or persistence mechanisms, which are important for a state-saving tool.

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 50% (only 'summary' has a description). The description adds value by explaining what to capture in 'summary': 'in-progress work, blocked items, completed items, key decisions,' which clarifies the parameter's purpose beyond the schema. However, it doesn't address the 'tags' parameter, leaving half the parameters with minimal guidance.

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's purpose: 'Save current session state before conversation ends or context compresses.' It specifies the verb 'save' and resource 'session state,' and distinguishes from siblings like 'load_session' by focusing on preservation rather than retrieval. However, it doesn't explicitly differentiate from other memory-related tools like 'add_memory,' leaving room for slight ambiguity.

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 provides explicit usage guidance: 'before conversation ends or context compresses.' It implies an alternative by mentioning 'The next agent instance loads this automatically,' referencing 'load_session' as the complementary tool. This clearly indicates when to use it (pre-context loss) and ties it to sibling functionality.

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