open_partition

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

With no annotations, the description carries the behavioral burden. It discloses meaningful semantics: writes tag into the partition, sweep uses tombstones, and a context partition erases its records at close. It does not cover idempotency or permissions, but the described lifecycle behavior goes well beyond the bare schema.

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 main purpose is front-loaded in a clear first clause, and the additional lifecycle details are dense but useful. The CNIL parenthetical is non-operational and could be trimmed, but the overall description is compact relative to the complexity it covers.

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 description covers partition semantics and the related lifecycle tools well, but omits operational details such as return behavior, what happens if a partition with the same name already exists, and whether opening is idempotent. Since there is no output schema and no annotations, these gaps leave an agent with some uncertainty.

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?

The input schema has 0% description coverage, so the prose is the only real semantic source. The description maps the core concepts: 'named scope' corresponds to name, 'per agent or per process' relates to agent/kind, 'size cap' maps to max_records, and 'expiry' maps to max_age_days. It explicitly explains the kind values, though it leaves some nullable/default behavior to be inferred.

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 states a concrete verb and resource: 'Open a memory partition', and defines it as 'a named scope per agent or per process with a size cap and an expiry'. It also names the sibling lifecycle tools and how they relate, so an agent can distinguish open_partition from remember_in_partition, sweep_partitions, and close_partition.

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 lifecycle context: writes via remember_in_partition are tagged into the partition, sweep_partitions applies the size/expiry constraints, and close_partition ends the process. This makes the surrounding workflow and the role of open_partition obvious, though it stops short of explicit when-to-use versus alternatives guidance.

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