recall

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

No annotations are provided, so the description carries the full disclosure burden, and it largely fails to: it does not say what is returned (snippets? full records? scores?), whether results are ranked, or what happens on empty matches. "Window-size adaptation" is the one genuine behavioral note, but it merely echoes the context_window_size parameter description in the schema.

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 sentences, front-loaded with the core verb and resource; nothing is padded. The second sentence is a compressed feature fragment rather than prose, which is space-efficient but slightly telegraphic, keeping it just below a 5.

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?

This is a 13-parameter retrieval tool with no annotations and no output schema, so the description should cover return shape, result ranking, and default behavior. It covers none of these, leaving an agent unable to predict what a call yields or how to interpret empty/oversized results.

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 92% — tags, limit, sort_by, memory_type, include_shared, include_archived, include_superseded and context_window_size are all documented inline. The description adds no parameter-level meaning beyond this, so the baseline 3 applies; the only slight addition is characterizing the matcher as keyword-based, which implies the query is not vector/semantic search.

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+resource pair ("Search and retrieve relevant memories") that is clearly a retrieval operation, distinct in spirit from the write-oriented siblings like remember/archive_memory. However, it never names list_memories, the closest sibling, so the search-vs-list boundary is left for the agent to infer.

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 offers no when-to-use, when-not-to-use, or alternative-tool guidance. An agent cannot tell from this text whether to call recall, list_memories, or remember for a given information need; the fragment "Keyword match + filters + sort" hints at capability but not at selection criteria.

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