nanomem_search

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

With no annotations provided, the description carries the full behavioral burden and handles it well: it discloses that SUPERSEDED results are historical-only and must not be treated as current truth, and that an incomplete-match state is flagged on the last line and should be trusted ('counted, not estimated'). These are genuinely useful behavioral traits beyond any structured field.

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?

Three sentences, purpose front-loaded in the first, followed by two tightly-worded behavioral notes that each earn their place. No fluff, though the phrasing is slightly dense and could be lightly trimmed.

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?

Despite no output schema and no annotations, the description explains the two critical interpretation edge cases (SUPERSEDED semantics and the completeness line) that an agent must understand to use results correctly. Minor gaps remain — normal result format and ordering are unspecified — but the essential semantics are covered.

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% and the schema descriptions are already rich (min_score explains the cosine floor and the relevance-count caveat). The tool description adds no parameter-specific detail, so it neither improves nor harms — baseline 3 is correct because the schema does the heavy lifting.

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: 'Search persistent long-term memory for relevant past facts and context.' The purpose is unmistakable and implicitly distinguishes from siblings (nanomem_add writes, nanomem_stats aggregates, nanomem_changes tracks edits) — search is a retrieval operation clearly separate from them.

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 description implies when to use it (when past facts are needed for answering) but never names alternatives or exclusion conditions. Sibling tools are not mentioned, so an agent must infer that search, not history/stats, is the retrieval path. The SUPERSEDED and last-line guidance is interpretation advice 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.