Recall Memories

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

Annotations already declare readOnlyHint=true, idempotentHint=true. The description goes well beyond this by disclosing search behavior: 'The search splits your query into individual words and matches each one against titles, content, and tags. Results are ranked by how many keywords match.' It also adds context about cross-model memory coverage. No contradictions; the description complements annotations.

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 structured with clear sections: pre-prompt, function statement, critical instructions with examples, args list, and return note. It is front-loaded with the most critical usage instruction. However, the 'Args' section partially duplicates the input schema, which increases length without adding information. Still, the extra examples and emphasis make the length worthwhile.

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 6-parameter tool with no output schema, the description is remarkably complete. It explains when to use, how to search effectively (keywords, tags, categories), what results look like ('Matching memories ranked by keyword match count'), and accommodates edge cases (e.g., 'If unsure what to search for, use broad single keywords'). It covers all necessary operational aspects.

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 baseline is 3. The description adds practical value beyond the schema through specific query examples (GOOD vs BAD queries), tag usage guidance ('ALWAYS pass relevant tags when you know them'), and keyword length recommendations. These enrich the schema's already detailed descriptions, justifying a 4.

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 clearly states the tool's function: 'Search and retrieve relevant memories from FlowMCP.' It uses a specific verb ('Search and retrieve') and resource ('memories from FlowMCP'), and distinguishes itself from siblings like store, forget, list_spaces by emphasizing retrieval of existing memories for context loading. The pre-prompt reinforces its role as a memory retrieval tool.

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, actionable usage guidance: 'You MUST call this tool AT THE START of ANY conversation that references...' and 'Use this at the start of conversations to load user context, before giving advice, or whenever the user references previous work.' It also explains when to use it versus the agent's built-in memory, effectively differentiating it from alternatives.

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