save_memory

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

With no annotations, the description carries the full burden and does so: it discloses the side effect that 'replaces' flags the earlier memory OUTDATED and that searches then answer with the new one first, and the failure path where nothing is flagged and candidates are listed. It also states the tool reports filing location and contradictions that should be relayed.

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?

Front-loads purpose and scope in the first sentence, then the inclusion/exclusion rule, then a compact per-argument block. Given zero schema coverage, the args section is necessary rather than redundant, and no sentence is filler.

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?

A four-parameter write tool with no annotations and no output schema explanation needed; the description still notes the return signal to relay. Everything an agent needs to invoke it correctly, including the cross-memory side effect, is present.

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, and it does for all four parameters: content (self-contained, date-prefixed), domain (default 'general' with a concrete example 'software.java'), content_type (enumerates values with 'auto' recommended), and replaces (meaning plus example 'RainDesktop version 1.3' and multi-match behavior).

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?

States a specific verb and resource ('Store durable knowledge in the user's long-term memory (IHMT)') and immediately scopes it with what belongs and what does not. The 'IHMT' naming and the 'replaces' semantics clearly separate it from search_memory/recall/mark_outdated.

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 when-to-use ('decisions and why, setup, preferences, people and projects, procedures'), when-not ('not transient chat, not secrets'), plus formatting rules (self-contained, date prefix) and a named fallback to mark_outdated when several memories match. Routing is fully specified.

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