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

Annotations cover idempotency and non-destructiveness, and the description adds real value on top: it discloses the mode-dependent behavior (summary returned when confirm is absent vs. acceptance recorded when true), the contents of the dry-run response, and the cross-tool gating requirement. The 'Safe to repeat' note reinforces rather than contradicts idempotentHint=true.

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-loads purpose and the gating requirement, then walks the flow in sequence with no filler sentences. Slightly long compound sentences keep it from a 5, but every sentence carries 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?

There is no output schema, and the description compensates by describing what the non-confirm call returns (terms summary, full-terms link, prior acceptance status). For a one-parameter boolean tool this is fully self-contained.

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 100% and the single parameter is already documented with the same intent ('true only after the user has agreed'). The description restates that semantics in flow context but adds no new syntax or format detail, so the baseline of 3 applies.

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 ('accept') and resource ('Errands terms') and immediately explains its role as a gate: 'needed before any AI call or errand can dial.' This distinguishes it from the many errand/call siblings without the agent needing to open a 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 an explicit two-phase protocol: call without confirm to fetch the summary, show it to the user, then call again with confirm=true only after clear agreement. The precondition (must be accepted before AI calls/errands) is spelled out, leaving nothing to inference.

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