nanomem_add

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

No annotations exist, so the description carries the full burden. The entity parameter usefully discloses the supersede semantics (same entity value lets nanomem know which statement supersedes which) and the fallback lexical tagger's poor performance on narrative phrasing. However, the main description stays silent on return behavior, whether identical facts are deduplicated, or whether writes are reversible.

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 single, front-loaded sentence with zero waste, and the schema carries the operational detail — the right division of labor. It is slightly sparse on behavior, but that is a completeness concern rather than a conciseness defect.

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 4-parameter write tool with no output schema and no annotations, the definition covers the entity semantics well but never states what the agent gets back on success (e.g., an ID or confirmation), nor does it note error conditions. The rich entity parameter offsets some of this, but the write path remains under-specified.

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 coverage is 100%, so the baseline is 3, and the entity description clearly exceeds it: it explains the mechanism (same value = supersede), gives concrete examples ('employer', 'home_address', 'phone'), and warns that omitting it triggers a tagger that 'guesses badly' on narrative phrasing. This adds genuine decision-making value beyond the schema field names.

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 uses a specific verb and resource ('Store a fact, note, or document into persistent long-term memory'), clearly identifying the write operation among read-focused siblings (search, history, as_of, stats, changes, volatility). It doesn't explicitly name or contrast a sibling, so it stops short of full differentiation.

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?

When to use this tool is implied rather than stated — the sibling names are all query operations, so the write-vs-read split is inferable, but the description never says 'use this to persist, use nanomem_search to retrieve.' The entity parameter does give operational guidance about when to omit it, which is useful but parameter-level rather than tool-selection guidance.

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