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

Annotations cover the safety profile (non-read-only, non-destructive, non-idempotent, closed-world), so the description's job is to add persistence and side-effect detail — which it does: it stores only the tool id and the enum, and it does not touch recommend_tools. It does not warn that repeated calls compound the ranking shift implied by idempotentHint=false.

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?

Four short sentences, front-loaded with what is adjusted, followed by data stored, scope exclusion, and the optional parameter. No sentence is filler; the telegraphic style is dense rather than vague.

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 three-parameter mutation with no output schema, the description covers purpose, persistence scope, sibling exclusion, and the optional key's cross-tool dependency. It leaves unstated what the ranking adjustment does in magnitude or whether it requires an existing preference feed.

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 0%, so the description carries the full burden. It adds real meaning for key (same feed key as set_preferences, scopes to that project's ranking) and constrains tool_id to a listed tool, though the action values merely restate the schema enum without describing their effect on ranking direction.

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?

Names a specific verb and resource: adjust this user's check_updates ranking for a listed tool. It also bounds the scope explicitly against siblings (check_updates for reading, recommend_tools explicitly unaffected), so an agent can distinguish it from log_choice or save_preferences without opening the schema.

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?

Gives a clear exclusion ("Does not change recommend_tools") that routes an agent away from expecting general recommendation tuning, and the optional key note ties usage to a prior set_preferences call. It stops short of stating positive when-to-use conditions versus log_choice or save_preferences.

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