Graph Decay

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

The description adds significant behavioral context beyond the destructiveHint annotation by detailing that decay is irreversible and requires a backup for restoration. It also mentions the return of counts per type. No contradiction with annotations (destructiveHint matches).

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 highly concise with three sentences. It front-loads the core action and then provides crucial warnings. Every sentence adds value, and there is no redundant or extraneous information.

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 (applies decay to all nodes/edges with per-type half-lives), the description covers the algorithm, context (dream process), irreversibility, preview option, and return counts. It lacks explicit half-life values beyond examples, but overall provides sufficient context for an agent to use 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 100% coverage with a single parameter (dry_run) that has a clear description. The tool description reinforces the parameter's purpose, but adds no new information beyond what the schema already provides. Baseline score of 3 is appropriate.

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 it applies time-based decay to node confidence and edge weights using per-type half-lives, with specific examples (preferences ~693d, events ~99d). It also mentions it's called by the dream process during maintenance. However, it does not explicitly differentiate from sibling tools like graph_weaken or graph_prune, leaving some ambiguity about when to use decay vs. alternatives.

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 usage guidance by recommending preview with dry_run=true first and warning that decay is irreversible without restoring from a backup. It also notes the tool is called during dream maintenance. However, it does not specify when not to use this tool or suggest alternatives, which would further improve guidance.

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