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

Annotations include readOnlyHint=false, but the description goes further: it states the tool 'writes up to 3 new memories back' (mutation), describes fallback behavior when the memory server is unreachable ('falls back to its own always-on store otherwise — never fails the call'), names the exact model used, and notes that the response includes the model name. No contradiction with annotations; the description adds substantial behavioral context.

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 dense but every sentence carries distinct information: core function, memory behavior, fallback, usage guidance, model, input, output, and cost. It is front-loaded with the primary purpose and structured to flow from what → when → how → returns. No filler or repetition.

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 complex tool with no output schema, but the description covers all critical aspects: memory read/write counts, semantic recall, fallback guarantee, model, cost, usage context, input shape, and a complete list of return fields. It also distinguishes siblings. Nothing essential is missing for an agent to invoke it 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 coverage is 100%, so baseline is 3. The description adds value by summarizing the input format ('Input: {think: string}') and enumerating the return fields, which is helpful since there's no output schema. However, it omits the aliases and the optional character scope, which the schema documents fully. Overall, it meaningfully supplements the schema without redundancy.

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?

Description opens with 'Reason over a question or task with your agent's own persistent memory in the loop' – a specific verb+resource+mechanism. It clearly differentiates from siblings: 'agent-memory covers plain store/recall' and 'agent-brain-smart runs the identical contract on claude-sonnet-5.' This is unambiguous about what the tool does and how it differs.

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?

Explicit usage guidance: 'Use for decisions that should build on what the agent already knows' and directly names the alternative for plain store/recall ('agent-memory'). It also references agent-brain-smart for a different model tier. This tells the agent when to pick this tool over its closest siblings.

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