synapse_retain

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

No annotations are provided, so the description carries the full behavioral burden. "Save" implies a persistent mutation, but nothing states whether writes are idempotent, whether duplicate facts are merged or duplicated, whether existing entries can be overwritten, or what identifier comes back. For a memory-write tool with zero annotation coverage, this leaves real gaps.

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?

A single front-loaded sentence with no filler; the verb leads and the accepted content types follow. It is efficient, though it stops short of the second sentence that would carry the missing usage and behavioral context.

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?

With no annotations and no output schema, the description is the only place to learn how this write behaves and what it returns, and it says nothing about either. For a mutation tool in a memory system with three sibling tools, the definition is under-specified relative to its complexity.

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 100%, so content, category, and salience are already fully documented, including the enum values and the 0.95+ salience guidance. The description's type list loosely echoes the category enum but adds no syntax, formatting, or content-granularity guidance beyond the schema. Baseline 3 is appropriate.

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?

"Save an atomic fact, architectural decision, permanent directive, or SOP" gives a specific verb and enumerates the resource types, which the opaque name "synapse_retain" does not convey on its own. It is clear what the tool does, but it never contrasts itself with the sibling synapse_record_episode, which by name plausibly also writes to the same memory store.

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 enumerated content types (atomic fact, decision, directive, SOP) implicitly scope when to use this tool, and the word "atomic" hints at granularity. But there is no explicit statement of when to prefer synapse_recall, synapse_record_episode, or synapse_get_stats, and no guidance on deduplication or repeat saves.

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