think

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

The description transparently discloses behavior: it processes memory consolidation, conflict scan, pattern mining (optional), and explains the maintenance cycle in detail. It notes that the tool modifies state (non-read-only) and is safe for frequent use. This adds significant context beyond the minimal annotations (readOnlyHint=false, etc.), with no contradictions.

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 with sections (DESIGNED TO BE CALLED OFTEN, MODES, Args) and front-loads key information. However, it is relatively lengthy with extensive parameter details in paragraph form. While every sentence adds value, a more compact list or table could improve clarity for quick scanning.

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 (18 parameters, multiple modes, no output schema shown), the description is comprehensive. It covers purpose, usage frequency, mode selection, parameter explanations, and behavioral effects. The presence of an output schema (not shown) means return values are not required in the description. All necessary context is provided for an agent to select and invoke the 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?

The input schema has 18 parameters with only titles and defaults (0% description coverage). The description compensates by listing and explaining each parameter's purpose (e.g., 'run_consolidation: Merge similar memories', 'consolidation_limit: Batch size'). While thorough, it does not provide exact syntax or constraints beyond the schema, but it adds meaningful semantics for an agent.

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: 'Run incremental cognitive maintenance — processes a small batch per call.' It identifies the tool as a maintenance/consolidation tool, distinguishing it from sibling tools like 'remember', 'recall', and 'forget' which are focused on individual memory operations. The description also outlines different modes (default, maintenance_cycle, last_cycle_only), further clarifying its role.

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 explicitly advises when to use the tool: 'DESIGNED TO BE CALLED OFTEN: Each call processes ~5 memories... Running regularly (e.g. at end of conversation) gradually maintains the entire database without blocking. Safe to call frequently.' It also explains when to use alternative modes like maintenance_cycle and last_cycle_only, providing clear context for invocation.

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