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

Annotations only cover the safety profile (readOnly, idempotent); the description adds genuinely new behaviour: newest-first ordering, the fact that test-mode rows are hidden unless include_test is true, the personal-data handling constraint, and the pagination caveat about comparing `total` with `limit`/`offset` before concluding completeness. It also sketches the returned fields despite there being no output schema.

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 purpose and contents, then usage, then filters, then caveats — a sensible information hierarchy. The PERSONAL DATA sentence is a policy instruction that consumes real space, but it does earn its place for a personal-data-returning tool; the paragraph is dense rather than padded.

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?

With no output schema and 12 parameters, the description carries real burden and mostly meets it: return contents, sort order, test-mode default, and pagination semantics are all stated. Gaps are modest — the `category` filter and the `user_goal` field go unmentioned, and there is no note on auth or empty-result behaviour.

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 description coverage is 100%, so baseline is 3. The description groups the filter parameters ('status', `form` slug, `search` on email/name, submitted-at window, `source`) which helps an agent see the filter surface at a glance, but it largely restates the schema and says nothing about `category` or how `limit`/`offset` combine with `total` beyond the pagination warning.

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?

Opens with a specific verb+resource ('List what visitors submitted through a site's forms') and adds scope details that matter: the Inbox, newest-first ordering, and full answer payloads (message, budget, custom questions) plus contact fields. An agent can distinguish this from list_forms (which presumably lists the forms themselves) and from export_submissions or delete_submissions without opening 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 concrete usage intents ('read, triage, summarise or judge leads') with real user-question examples, which tells the agent the right situations to reach for it. It does not name alternative siblings (export_submissions for bulk extraction, update_submission_status for triage actions, list_forms for discovery), so the negative case is left implicit.

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