memanto_recall

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

With no annotations, the description carries the full behavioral burden and does disclose the return shape (hits with content, score, metadata), the relevance-ranked 'semantic' nature of matching, the default limit of 10, and that filters/thresholds are optional. It does not state auth/permission requirements, result ordering, pagination beyond limit, or whether the search crosses agent boundaries — meaningful gaps for a tool with zero annotation coverage.

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?

Purpose is front-loaded in a single sentence, followed by an ordered Args block that mirrors parameter order, plus a brief Returns line. The Args entries mostly restate schema titles and defaults, which is mild redundancy, but there is no filler or hedging.

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 six-parameter tool with no annotations and full output schema, the description covers inputs and the general return shape adequately. Still missing are the valid memory_types vocabulary, the temporal distinction from the as_of/current siblings, and any note on result ordering or scope — gaps an agent would hit on first real use.

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: all six parameters get a one-line gloss (natural-language query, whose memory, type filter, tag filter, max results with default 10, confidence threshold). It stops short of a 5 because memory_types has no enum in the schema and the description never names the valid memory type values, leaving a required filter unbounded.

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: 'Semantic search over an agent's memory,' which is clearly distinct from memanto_remember (write) and memanto_answer (QA). However, it never distinguishes itself from the closest siblings memanto_recall_as_of and memanto_recall_current, so an agent cannot tell from the description alone which recall variant to pick.

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 when-to-use guidance at all — no statement of when to prefer this over memanto_recall_current, memanto_recall_as_of, or memanto_answer. Usage is only inferable from the tool name and the word 'search'; exclusions and alternatives are absent.

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