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

Annotations only say non-readonly, idempotent, non-destructive; the description adds the exact write footprint (one report per cause/app/day with later ones attaching to the first, plus an activity line attributed to the caller), which is consistent with idempotentHint=true. It also discloses data minimization (codes, counts, dates, app id, account reference; never page content, conversation, or logs), the refusal condition, the missing latency guarantee, and the requirement of a connected account.

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 critical fact ('This WRITES') is front-loaded and the payload/disclosure details follow logically. It is dense but nearly every clause carries new information; the heavy capitalization and stacked parentheticals make it slightly harder to scan than necessary.

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 two-parameter mutation with no output schema, it covers side effects, deduplication, data sent, refusal behavior, prerequisites, and what the user sees afterward. The only real omission is any explanation of the optional `dropId` argument.

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 50%: `cause` is documented in-schema as coming from dropyour_support actions[].args.cause, and the description reinforces that it is a closed vocabulary with no free text (matching the two-value enum). The optional `dropId` parameter is undocumented in both the schema and the description, leaving its role and expected format unexplained.

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 the specific verb and resource ('Report to Dropyour a defect of the PLATFORM') and scopes it to defects that dropyour_support already diagnosed, distinguishing it from the diagnostic sibling tool. The parenthetical '(side: platform, reportable: true)' pins the exact triggering condition from prior tool output.

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?

It gives an explicit precondition chain (the cause must come from dropyour_support and be on the platform side with reportable: true), an explicit exclusion (it is refused when the facts do not put the cause on the platform's side), and an explicit human-in-the-loop rule ('Ask the user before calling it'). Nothing about when to call it is left to inference.

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