recall_memories

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and idempotentHint=true, so the safety profile is fully covered. The description adds behavioral context by explaining ranking semantics ('ranked by semantic relevance'), the Phase 2 Knowledge Graph filtering capability, and filter behaviors like partial matching vs exact match for different filters. It does not describe pagination or total return behavior beyond the limit parameter, but the annotation coverage is strong.

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?

Well-structured with clear sections (BASIC SEARCH, FILTERED SEARCH, WHEN TO FILTER, COMBINED EXAMPLES) using emoji headers for visual scannability. The content is somewhat verbose with many examples, but each serves a distinct purpose (each filter has its own example). The combined examples at the end add practical value. Slightly longer than strictly necessary but well-organized and front-loaded with the core purpose.

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 10-parameter tool with no output schema, this description is remarkably complete. It covers all filter types with examples, provides usage timing guidance, distinguishes exact vs partial matching semantics, and gives combined real-world patterns. The sibling context shows this is a memory-retrieval tool among many, and the description effectively positions it as THE semantic memory search tool. No output schema exists, so return-format information would be valuable but the schema itself documents the limit parameter and the filter semantics are thoroughly 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 each parameter already has rich descriptions with usage guidance and examples. The description adds value by showing FILTERED SEARCH patterns, the Phase 2 context, and combined examples like recall_memories(query='auth', entity='purmemo', has_observations=true). It also corrects/clarifies the 'stakeholder' parameter mentioned in the combined example that wasn't prominently promoted. However, some of this is redundant with the schema descriptions.

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 states a specific verb+resource ('Search and retrieve saved memories') with clear semantic ranking. It distinguishes itself from siblings like recall_public (public memories) and get_memory_details (single memory lookup) through its filter-focused identity. The extensive examples reinforce the core purpose.

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?

Provides explicit WHEN TO FILTER guidance with concrete use-cases ('Use entity when user asks about specific person/project by name', 'Use intent when user asks for decisions'). The description explains when filters are needed for PRECISION over semantic similarity, and demonstrates combined usage patterns. It clearly distinguishes filtered vs basic search scenarios.

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