review_mode

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

Annotations cover the safety profile (readOnlyHint=false, destructiveHint=true), and the description adds real context beyond them: set requires an explicit user request in-chat, user_request must quote the user's words, and every change is logged with them. It also explains the project-override lifecycle (clear=true removes it). It does not spell out the full consequence of the destructive flag for future captures, but the effect on queueing is described.

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?

Front-loaded purpose followed by mode semantics and then the safety directive, with no filler sentences. It is dense and slightly crammed with directives, but each clause carries distinct operational meaning for a policy tool.

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 7-parameter, no-output-schema tool the description covers the critical behaviors: mode meanings, override scoping, and the set precondition. It does not describe what action=get returns, which is a modest gap given no output schema exists, but nothing needed to invoke it safely is missing.

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 71%, and the description extends it: it defines each mode value in prose (off/auto_only/types/everything), ties mode=types to the kinds list, and clarifies the project/clear override semantics versus the install-wide default. Only 'model' is left to the schema alone, a minor gap.

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?

States a specific verb pair (read/change) plus the resource (review mode) and immediately defines what it governs: which new records wait in the review queue. The get/set distinction is spelled out, so an agent can tell what each call does 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 explicit conditions: action=get is read-only, action=set ONLY when the user has explicitly asked in this chat, and an explicit prohibition ('never change it on your own initiative or to get your writes saved'). This is a clear when/when-not rule, which is exactly what an agent needs for a policy-setting tool.

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