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

Annotations already declare this is a non-read-only, non-destructive, non-idempotent, closed-world write. The description adds genuinely useful behavioral constraints beyond that — a secrecy/data-handling rule (no secrets, customer data, site names) and a consent precondition for reviews — which is real value. It does not say where the submission goes, whether it can be edited or retracted, or what the caller gets back after sending.

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?

It is short, but telegraphic to the point of obscurity: colon-led fragments and semicolon chains ('type review: only after the human said yes and saw the text; about Checkbox, not the site: no site names...'). No sentence is wasted, yet the structure forces the agent to re-parse to separate the review rules from the general content rules.

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 an 11-parameter write tool with no output schema and no per-parameter schema docs, the description covers the content fields well but leaves the context fields (site, tool, request_id, would_keep_using) unexplained and never says what happens after submission. Nothing about it is wrong, but an agent could fill required-looking identifiers incorrectly or omit the keep-using signal entirely.

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 0%, so the description carries the load and largely does: it defines the type enum meanings, the message contents (what you tried, happened, expected), score as a 0-10 recommend rating, the ≤5-phrase limit and 'check.id: why wrong' format for wrong_verdicts, and an example format for stack. Four parameters (site, tool, request_id, would_keep_using) get no mention at all, which is why this isn't a 5.

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 never states the action explicitly (no 'send' verb or 'feedback to the team'); it relies on the title to establish purpose and instead opens with content guidance. It does distinguish the four submission types (bug/idea/question/review), which lets an agent infer this is a feedback-submission tool rather than a check/scan tool. The gap: a reader of the description alone cannot say what the tool does in one sentence.

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?

There is strong, specific when/when-not guidance for the 'review' path: only after a human has said yes and seen the text, and only about Checkbox rather than the site. Prohibited content is enumerated (site names, URLs, quotes, secrets, customer data, legal claims). What's missing is guidance on when to reach for this tool at all versus siblings like suggest_improvements, but no alternative produces comparable confusion.

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