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

With annotations indicating destructiveHint=true and readOnlyHint=false, the description adds substantial behavioral context: updates require full policy and confirmed:true, existing policies remain unchanged, never raise autonomously, and includes domain-specific rules about credits and reservations. This goes well beyond what annotations provide and is very helpful for safe invocation.

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 and front-loaded with critical information: read vs update context, credit value, defaults, update requirements. Every sentence carries useful information. It could be slightly more structured (e.g., bullet points for update requirements), but it's efficient and avoids fluff.

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 (read/update, policy object, destructive potential), the description covers key aspects: consent requirement, default policies, update mechanics, and side constraints. It does not explain the 'action' parameter's expected values or the read operation's return format, but an output schema exists, so return values needn't be described. It's nearly complete but misses a few details.

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 description coverage is 0%, so the description must compensate. It does: it explains the policy structure (enabled, taskPoints, fiveHourPoints, dayPoints, weekPoints, revision, unlimited), the need for full policy including unlimited, and confirmed:true requirement. It also clarifies credit conversion and default limits. This adds significant meaning beyond the bare schema, though it doesn't detail the 'action' parameter's allowed values (e.g., 'read' vs 'update').

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 states a clear dual-purpose tool: read account-wide authorization policy or update it. The verb+resource is specific and distinguishable from siblings like 'account' or generation tools. However, it lacks an explicit statement of when to use this versus 'account', which might also expose policy information, so it's not a perfect 5.

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 strong usage guidance: 'update only with explicit user consent', 'Never raise autonomously', and details about default policies. It clearly distinguishes read vs. update actions. It doesn't explicitly mention alternatives or when not to use this tool (e.g., vs. 'account'), but the context is quite clear.

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