open_partition

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

With no annotations, the description carries the full burden, and it is unusually transparent. It discloses reopening behavior (returns existing partition if rules match, refused if they differ), rule immutability, context-partition erasure on close, tombstone behavior during sweep, and the fact that the result reads back the rules in force from the registry.

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 efficiently front-loaded with the core definition, then covers lifecycle and reopening behavior in four dense sentences. The middle sentence chains several tool references, making it slightly heavy, but every sentence contributes non-redundant information.

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?

For a five-parameter tool with no annotations and no output schema, the description is substantial: it explains the contract, lifecycle, reopening rules, and result content. Remaining gaps are the exact composition of the 'rules', null semantics for max_records/max_age_days, and kind/agent parameter combinations, but an agent can still call it correctly in most cases.

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. It maps kind to context/process/agent, name to the named scope, max_records to the size cap, and max_age_days to the expiry, and it references the agent dimension. It does not fully clarify the relationship between kind and the agent parameter or the meaning of null limits, but the core semantics are provided.

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: 'Open a memory partition' and immediately defines it as a named scope with a size cap and expiry. It names the lifecycle siblings (remember_in_partition, sweep_partitions, close_partition), making the tool easily distinguishable from them, and even spells out the allowed kind values.

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 workflow context: remember_in_partition is for writes, sweep_partitions enforces the cap/expiry, and close_partition ends the process. This effectively routes an agent to the right sibling. It stops short of explicit 'do not use when' conditions, but the lifecycle mapping is clear.

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