remember_in_partition

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

With no annotations present, the description carries the full behavioral burden and does so thoroughly. It discloses tagging, cap enforcement, oldest-eviction with tombstones, expiry/close erasure, PROJECT-scope stamping, return contents, blocked-write verdicts, and guard behavior for objectless keys. This goes far beyond what the name or schema alone would reveal.

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 a dense paragraph, but every sentence contributes behavioral or return-value information. It is front-loaded with the core 'remember into a partition' concept, and only the final guard-related sentence is somewhat cryptic yet still relevant.

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 complexity, the absence of annotations, and the lack of an output schema, the description explains the full lifecycle of a partitioned record, the return verdict, and a non-obvious guard edge case. It is not fully complete because tags are left undefined and the guard retirement behavior assumes prior knowledge, but an agent can call the tool with reasonable confidence.

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 adds meaningful semantics for 'partition' and 'key', including partition tagging and keyed-write guard behavior, but it never explains 'text' or 'tags'. The description partially compensates for the schema gap but not completely.

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 identifies the operation as 'remember into a partition', explaining that records are tagged partition:<name>, counted against a cap, and erased on expiry or close. It uses a specific verb and resource, and the partition-specific mechanics distinguish it from the sibling 'remember', though it does not explicitly name that alternative as a decision point.

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?

Usage is implied by the first sentence: this is the tool for remembering a record into a partition. It references the sibling 'remember' for the return shape, but does not explicitly state when to choose this tool over 'remember' or other partitioning-related tools like open_partition or close_partition.

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