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

Adds substantial context beyond the annotations: costs one doc-export credit, saves to YOUR OWN Drive rather than the prospect's, degrades unknown keys to "N/A" instead of erroring, returns a one-line fix instead of a raw error when Google isn't connected, and explains that agency_appendix never surfaces in client-facing exports. This is exactly the behavioral detail annotations can't convey.

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 purpose and output medium are front-loaded, and the dense run-on sentence still carries mostly load-bearing detail (credit cost, Drive ownership, degradation behavior, two-version workflow). It is longer than ideal for a single paragraph but wastes little.

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 tool with no output schema and an open-world write, the description covers prerequisites, cost, failure handling, and the returned shareable link. The one unexplained element is the destructiveHint=true annotation, since creating a new doc is not described as overwriting anything, leaving a small behavioral gap.

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%, so the baseline is 3, and the description genuinely adds meaning: it explains that report_data must be built from prior audit output plus the agent's own writing, specifies executive_narrative as client-facing prose to personalize against style_reference, and defines the opt-in nature of agency_appendix. That is real semantic value beyond the schema text.

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 and artifact: render findings into a branded Deloitte-style document saved as a Google Doc in your own Drive, returning a shareable link. It names the source tools (get_prospect_audit / site audit tools), but does not differentiate from nearby siblings like generate_report, download_report, or get_audit_report, so an agent must infer the split.

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?

Explains context clearly: usable for either a prospect audit or a normal site audit, requires Google connected with Drive permission, and calls out the two-call pattern (client version with appendix omitted vs agency copy with it included). No explicit when-not or direct routing against the report-generating siblings.

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