memory_read

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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context: memory is shared across sessions and tools, results are ranked by relevance or recency, and each result carries an id for feedback. It also clarifies that corrections are done via memory_write, not deletion. The only minor gap is not describing the exact return format, but given the annotations and the description's richness, a 4 is appropriate.

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 well-structured and front-loaded with the core purpose. It's a bit long but every sentence earns its place, covering usage guidance, behavioral notes, and parameter caveats. The use of bold for 'ALWAYS' and warnings like '⚠️' helps highlight key points. It's slightly verbose but not wasteful, so a 4 is appropriate.

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?

Given the tool's complexity (7 parameters, shared memory, multiple siblings), the description is remarkably complete. It covers when to use, when not to, alternatives, parameter caveats, and behavioral traits. The output schema is absent, but the description mentions that results carry an id for feedback, which is sufficient. No critical information is missing for an agent to call this tool correctly.

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 100%, so the schema already documents all parameters. The description adds value by explaining the top_k caveat (not a hard cap, can return more or fewer), the domain parameter's behavior (own domains vs shared rooms), and the exclude_author warning (not usable from here). This goes beyond the schema's basic descriptions, providing critical usage nuances. A 4 is justified because it adds meaningful semantics beyond the schema.

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 purpose: searching long-term memory for prior context, preferences, decisions, etc. It distinguishes itself from siblings by explicitly mentioning memory_list_recent and memory_feedback, and by noting that it searches own domains vs shared rooms. The verb 'search' and resource 'long-term memory' are specific and unambiguous.

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 provides explicit guidance on when to use this tool: 'ALWAYS check here first when you're unsure whether you already know something' and when not to: 'no need to call it for general world knowledge you already hold.' It also names alternatives: memory_list_recent for complete bounded listings, memory_feedback for feedback, memory_write for corrections, and memory_list_rooms for room addresses. This is exemplary usage guidance.

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