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

Goes well beyond the annotations by disclosing that a rebuild consumes a banked entitlement, that holds/checks can refuse a request, that BDK builds and signs but the customer submits, that Android output is an .aab rather than a phone installer, and that secrets must never be pasted into chat. These are material consequences an agent cannot infer from destructiveHint/openWorldHint alone.

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 with the highest-stakes rule (approval required) and then moves through rebuild accounting, action routing, download semantics, and safety. It is dense and a few clauses are tightly packed, but nearly every sentence carries distinct operational content.

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 destructive, non-idempotent, open-world tool with five parameters and no output schema, the description supplies consent requirements, entitlement accounting, action routing, refusal behavior, artifact formats, and secret-handling policy. Nothing essential for correct invocation 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 100% and the enum descriptions are verbose, so the description largely restates them; however it adds operational framing (e.g., that confirm_build follows a customer yes, that free_rebuild is legacy-only) that ties parameters to the consent workflow. The marginal gain over the schema is modest but real.

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 names the verb and resource precisely ('Request a build or rebuild') and then enumerates the three actions the tool actually performs (request, status, download), including what each returns. It also explicitly distinguishes itself from bdk_next, so an agent can separate it from siblings without reading schemas.

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 preconditions ('only after explicit approval of that request and the saved settings'), per-path rules (confirm_build for first build, confirm_consumes_rebuild for ledger rebuilds, free_rebuild legacy-only), and a direct alternative ('action:status lists delivered history, not the current request; use bdk_next'). Guidance is complete and includes exclusions.

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