save_memento

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

With no annotations provided, the description carries the burden of behavioral disclosure. It does reveal a persistence trait (across sessions), the scope-decision requirement, and the prerequisite call. However, it doesn't disclose whether save_memento overwrites existing mementos, whether deletion is possible, or what the response returns. These are gaps given zero 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?

Two sentences containing the core purpose, the decision responsibility, and the prerequisite. No wasted words. Slightly more could be added about boundaries or behavior, but the current content is efficient and front-loaded.

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?

The tool has 4 params and no output schema, but schema covers 100% of parameters. The description reasonably covers purpose, the scope-decision, and sequencing. However, for a persistent-storage mutation tool with no annotations and no output schema, more detail on overwrite behavior, return values, and scope-selection heuristics would improve completeness.

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 all 4 parameters have schema descriptions. The description itself adds limited parameter meaning beyond the schema—it clarifies that 'scope' involves a decision the agent must make (global vs repo) and that text is the memento content. It doesn't clarify tags format beyond schema, and 'expires' formatting is fully in schema. Baseline 3 is appropriate since the schema does the heavy lifting.

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?

Description states it 'Saves a persistent memento across sessions' with a specific verb+resource. It distinguishes itself from siblings by noting the tool's scope-selection responsibility (global vs repo). However, it doesn't explicitly differentiate from save_memento_attachments or save_conversation beyond the core save action.

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 clear context by stating the agent must choose between global and repo scope. It also provides an explicit prerequisite: 'Requires init_memento or get_mementos first.' This is useful guidance about sequencing, though it doesn't name specific sibling alternatives or when-not-to-use scenarios.

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