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

With no annotations, the description carries the full burden and largely succeeds: it discloses that no state is committed ("This only makes a draft"), that the response contains the draft, terms and a token, and that both must be shown to the user. It does not mention auth requirements or rate limits, and the legal meaning of "terms" is left unspecified, so not quite complete.

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 two-step framing and the draft-only caveat are front-loaded, and the conditional field map is packed into dense but purposeful clauses with no filler. The middle sentence is long and slash-delimited, which costs a little scannability, but nothing is redundant.

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 12-parameter mutation-adjacent tool with no annotations and no output schema, the description covers the essential gaps: it explains the write is deferred, describes the return payload shape, and documents the conditional parameter branches. Remaining gaps (what the terms are, whether the episode identifier accepts a status id vs a number) are minor and partly covered by schema descriptions.

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 only 17% across 12 parameters, so the description must compensate, and it does for the core branch map: title/summary/translation map to the wrong-text and corrected-text fields, characters to the add/remove lists, arc to an id from list_arcs, number to the episode number, other to a single sentence. It adds no meaning for episode_id_or_number, panel number, or the mandatory acknowledgment boolean, leaving a few gaps the schema alone must cover.

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 opening clause names a specific verb and resource ("privately telling the site operator about a factual error in one episode's page") and states the scope constraint "one point per report." The phrase "Step 1 of 2" plus the explicit contrast with send_confirmed_error_report makes it distinguishable from that sibling without opening either 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?

It names the alternative (send_confirmed_error_report) and the precise condition that selects it: only after showing the draft and terms to the user and only if they say yes. It also gives explicit per-branch instructions for which fields to fill, which is exactly the routing guidance an agent needs for a polymorphic tool.

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