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

The description adds real behavior beyond the annotations: persistence across sessions and model changes, and an importance scale of 1-5 (the schema only shows a default of 3). However, it omits behavior an agent would want given idempotentHint=false, such as whether re-storing the same text creates duplicates or overwrites. With annotations already covering the safety profile (non-destructive, non-idempotent, closed-world), a 3 is appropriate.

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?

Two short, front-loaded clauses with no wasted words; the core purpose and the persistence benefit come first. It is efficient but fragmentary, and the terse style is part of why the other parameters go unexplained.

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?

An output schema exists, so return values need not be described, but for a 6-parameter mutation tool with zero schema documentation the description is too thin. Key fields like kind, source, and session are left opaque, and duplicate-handling behavior is unaddressed.

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% across 6 parameters, so the description must carry the burden and it does not. It explains only tags and the importance range 1-5, leaving kind, source, session, and text entirely undocumented in either place.

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 gives a specific verb and resource ("Store a fact") plus a distinguishing persistence trait ("survives sessions and model changes") that separates it from retrieval siblings like soma_recall. It never names an alternative tool explicitly, so sibling differentiation is implied rather than stated.

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?

There is no explicit when-to-use or when-not-to-use guidance, and no routing to alternatives such as soma_cold_put or soma_claim, which plausibly also store data. The only hint is "Tags for search", which implies later retrieval but does not define selection criteria.

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