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

Annotations declare the write/non-destructive/non-idempotent profile, and the description adds genuinely new behavior: submissions are reviewed ('Checked before it goes live') and require user confirmation first. It still doesn't say what happens after submission or how the correction is tracked, but the moderation and consent details are real value beyond the annotations.

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?

Three short sentences, zero filler: what it does, what happens to the report, and the consent requirement. The purpose is front-loaded and each sentence earns its place.

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 mutation tool with no output schema and no annotations covering the review workflow, the description supplies the two missing essentials: moderation timing and the confirm-before-send rule. Minor gap: it doesn't clarify that `id` is the restaurant identifier or what a successful submission returns.

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 only 25% — just `value` is documented — so the description carries extra burden. The examples ('dead phone number, new timings, a closure, a move') do implicitly clarify the `field` enum and what `value` should contain, but `id` (the 10-14 char target identifier) and `evidence_url` are never explained. Partial compensation, not full.

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?

Specific verb (tell/report) plus resource (a correction about a restaurant) with concrete examples — dead phone number, new timings, closure, move — that map directly to the enum fields. It is unambiguously distinct from the read-only siblings (get_place, search_restaurants), though it never names them.

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?

'Ask the user before sending' is an explicit precondition that governs when this tool may be invoked, which is unusually actionable guidance. It lacks any when-not guidance or explicit alternative, but for a submission tool the confirmation rule is the operative constraint.

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