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 of behavioral disclosure, and it does so thoroughly. It explains return statuses, deduplication behavior, pending user-inference claims, groundedness gating, drift monitoring, curation hints, and override flags. It even discloses that misattribution 'sticks' and that the user gets veto power, which is valuable behavioral context.

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 long, but the tool is complex with 14 parameters and many return statuses. It is well-structured with clear sections: intro, parameters, return statuses, and curation hint. It is front-loaded with the core purpose and every sentence adds necessary operational detail; there is no filler or redundancy.

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 complexity, the description is remarkably complete. It covers all major behaviors, return statuses, edge cases, override mechanisms, and even a passive curation notification. The output schema exists, but the description goes beyond it by explaining the meaning of each status and the conditions under which each is returned.

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 compensate for all 14 parameters. It explains content, scopes, category with subcategories, confidence, source, claims, groundedness_check, source_transcript, acknowledge_ungrounded, acknowledge_user_claim, and force=True overrides. It maps each return status back to relevant acknowledge_* flags, providing meaning far beyond the bare schema.

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 and resource: 'Create a new memory.' It clearly states when to call it ('Call PROACTIVELY when something durable enters the conversation') and distinguishes it from related tools by referencing memory_write_confirm, memory_write_cancel, memory_health, memory_remove, and memory_verify. This is a strong, unambiguous purpose statement.

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?

Explicit usage guidance is provided: 'aggressive writing is safe; the guardrails below catch bad writes.' It also gives category-specific guidance, warns against the catch-all 'general' scope, and explains when to use memory_write_confirm/cancel for user-inference claims. The description names alternatives for resolving issues, making the when-to-use decision clear.

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